{
 "cases": [
  {
   "id": "CASE-001",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-002",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-003",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-004",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-005",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "qwen-3.8-2.4t": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-006",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "FAIL",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-007",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "minimax-m3": "FAIL",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-008",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-009",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-010",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-011",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "FAIL",
    "gpt-oss-120b": "FAIL"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-012",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "FAIL",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "FAIL",
    "gpt-oss-120b": "FAIL"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-013",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "FAIL",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4.1-flash": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "FAIL",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "FAIL"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-014",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-015",
   "outcomes": {
    "claude-opus-5.5": "FAIL",
    "claude-opus-5.5.cc": "FAIL",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4.1-flash": "FAIL",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "FAIL",
    "gpt-6-astra": "FAIL",
    "gpt-6-astra.codex": "FAIL",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "FAIL",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "FAIL",
    "qwen-3.8-2.4t": "FAIL",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-016",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "kimi-k3": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-017",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "FAIL",
    "gpt-6-astra.codex": "FAIL",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-018",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-opus-5.5": "FAIL",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4.1-flash": "FAIL",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "FAIL",
    "qwen-3.8-2.4t": "FAIL",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-019",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-020",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-021",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-022",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-023",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-024",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "FAIL",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-025",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-026",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-027",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "FAIL",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "FAIL",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-028",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "FAIL",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-029",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-030",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-031",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-1"
  },
  {
   "id": "CASE-032",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "FAIL",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-033",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-034",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-035",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-036",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "FAIL",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "FAIL",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-037",
   "outcomes": {
    "claude-opus-5.5": "FAIL",
    "claude-opus-5.5.cc": "FAIL",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "FAIL",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "FAIL",
    "gpt-6-astra": "FAIL",
    "gpt-6-astra.codex": "FAIL",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "FAIL",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "FAIL",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-038",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "FAIL",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-039",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "FAIL",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "FAIL",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "FAIL",
    "qwen-3.8-2.4t": "FAIL",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-040",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "FAIL",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-041",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-042",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "FAIL",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "FAIL",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-043",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-044",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-045",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-046",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-047",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "FAIL",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-048",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-049",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-050",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-051",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-052",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "FAIL",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-053",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-054",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-055",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "FAIL",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "FAIL",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-056",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-057",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-058",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-059",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-2"
  },
  {
   "id": "CASE-060",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "FAIL",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-061",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-062",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "FAIL",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "FAIL",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-063",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-064",
   "outcomes": {
    "claude-opus-5.5": "FAIL",
    "claude-opus-5.5.cc": "FAIL",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-065",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-066",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "FAIL",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "FAIL",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-067",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "FAIL",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "FAIL",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-068",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "claude-opus-5.5.v2": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4-pro.v2": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "deepseek-v4.1-flash.v2": "PASS",
    "gemma-4-31b": "FAIL",
    "gemma-4-31b.v2": "FAIL",
    "glm-5.3": "PASS",
    "glm-5.3.v2": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-6-astra.v2": "PASS",
    "gpt-oss-120b": "FAIL",
    "gpt-oss-120b.v2": "FAIL",
    "kimi-k3": "PASS",
    "kimi-k3.v2": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "mimo-v2.6-pro.v2": "PASS",
    "minimax-m3": "PASS",
    "minimax-m3.v2": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-2.4t.v2": "PASS",
    "qwen-3.8-max": "PASS",
    "qwen-3.8-max.v2": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-069",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "FAIL",
    "qwen-3.8-2.4t": "FAIL",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-070",
   "outcomes": {
    "claude-opus-5.5": "FAIL",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4.1-flash": "FAIL",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "FAIL",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-071",
   "outcomes": {
    "claude-opus-5.5": "FAIL",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "FAIL",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "FAIL",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "FAIL",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-072",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "FAIL",
    "claude-opus-5.5.cc": "PASS",
    "claude-opus-5.5.v2": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4-pro.v2": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "deepseek-v4.1-flash.v2": "PASS",
    "gemma-4-31b.v2": "FAIL",
    "glm-5.3": "PASS",
    "glm-5.3.v2": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-6-astra.v2": "PASS",
    "gpt-oss-120b": "FAIL",
    "gpt-oss-120b.v2": "FAIL",
    "kimi-k3": "PASS",
    "kimi-k3.v2": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "mimo-v2.6-pro.v2": "FAIL",
    "minimax-m3": "PASS",
    "minimax-m3.v2": "PASS",
    "qwen-3.8-2.4t": "FAIL",
    "qwen-3.8-2.4t.v2": "PASS",
    "qwen-3.8-max": "PASS",
    "qwen-3.8-max.v2": "FAIL"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-073",
   "outcomes": {
    "claude-opus-5.5": "FAIL",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "FAIL",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-074",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "claude-opus-5.5.v2": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4-pro.v2": "FAIL",
    "deepseek-v4.1-flash": "FAIL",
    "deepseek-v4.1-flash.v2": "FAIL",
    "gemma-4-31b": "FAIL",
    "gemma-4-31b.v2": "FAIL",
    "glm-5.3": "PASS",
    "glm-5.3.v2": "FAIL",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-6-astra.v2": "PASS",
    "gpt-oss-120b": "FAIL",
    "gpt-oss-120b.v2": "FAIL",
    "kimi-k3": "PASS",
    "kimi-k3.v2": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "mimo-v2.6-pro.v2": "FAIL",
    "minimax-m3": "FAIL",
    "minimax-m3.v2": "PASS",
    "qwen-3.8-2.4t": "FAIL",
    "qwen-3.8-2.4t.v2": "FAIL",
    "qwen-3.8-max": "FAIL",
    "qwen-3.8-max.v2": "FAIL"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-075",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "kimi-k3": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-076",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "claude-opus-5.5.v2": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4-pro.v2": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "deepseek-v4.1-flash.v2": "PASS",
    "gemma-4-31b": "FAIL",
    "gemma-4-31b.v2": "FAIL",
    "glm-5.3": "PASS",
    "glm-5.3.v2": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-6-astra.v2": "PASS",
    "gpt-oss-120b": "FAIL",
    "gpt-oss-120b.v2": "FAIL",
    "kimi-k3": "PASS",
    "kimi-k3.v2": "PASS",
    "mimo-v2.6-pro": "PASS",
    "mimo-v2.6-pro.v2": "PASS",
    "minimax-m3": "PASS",
    "minimax-m3.v2": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-2.4t.v2": "PASS",
    "qwen-3.8-max": "PASS",
    "qwen-3.8-max.v2": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-077",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "FAIL",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "claude-opus-5.5.v2": "PASS",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4-pro.v2": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "deepseek-v4.1-flash.v2": "PASS",
    "gemma-4-31b": "FAIL",
    "gemma-4-31b.v2": "FAIL",
    "glm-5.3": "PASS",
    "glm-5.3.v2": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-6-astra.v2": "PASS",
    "gpt-oss-120b": "FAIL",
    "gpt-oss-120b.v2": "FAIL",
    "kimi-k3": "PASS",
    "kimi-k3.v2": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "mimo-v2.6-pro.v2": "PASS",
    "minimax-m3": "FAIL",
    "minimax-m3.v2": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-2.4t.v2": "PASS",
    "qwen-3.8-max": "PASS",
    "qwen-3.8-max.v2": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-078",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-079",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "FAIL",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "FAIL",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-080",
   "outcomes": {
    "claude-opus-5.5": "FAIL",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "FAIL",
    "qwen-3.8-2.4t": "FAIL",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-081",
   "outcomes": {
    "claude-opus-5.5": "FAIL",
    "claude-opus-5.5.cc": "FAIL",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "FAIL",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "FAIL",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-082",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-083",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-084",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "claude-opus-5.5.v2": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4-pro.v2": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "deepseek-v4.1-flash.v2": "PASS",
    "gemma-4-31b": "PASS",
    "gemma-4-31b.v2": "FAIL",
    "glm-5.3": "PASS",
    "glm-5.3.v2": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-6-astra.v2": "PASS",
    "gpt-oss-120b": "FAIL",
    "gpt-oss-120b.v2": "FAIL",
    "kimi-k3": "PASS",
    "kimi-k3.v2": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "mimo-v2.6-pro.v2": "PASS",
    "minimax-m3": "PASS",
    "minimax-m3.v2": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-2.4t.v2": "PASS",
    "qwen-3.8-max": "FAIL",
    "qwen-3.8-max.v2": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-085",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "claude-opus-5.5.v2": "PASS",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4-pro.v2": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "deepseek-v4.1-flash.v2": "FAIL",
    "gemma-4-31b": "FAIL",
    "gemma-4-31b.v2": "FAIL",
    "glm-5.3": "PASS",
    "glm-5.3.v2": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-6-astra.v2": "PASS",
    "gpt-oss-120b": "FAIL",
    "gpt-oss-120b.v2": "FAIL",
    "kimi-k3": "PASS",
    "kimi-k3.v2": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "mimo-v2.6-pro.v2": "PASS",
    "minimax-m3": "FAIL",
    "minimax-m3.v2": "PASS",
    "qwen-3.8-2.4t": "FAIL",
    "qwen-3.8-2.4t.v2": "PASS",
    "qwen-3.8-max": "PASS",
    "qwen-3.8-max.v2": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-086",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-087",
   "outcomes": {
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-088",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "FAIL",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-089",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "FAIL",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4.1-flash": "FAIL",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "FAIL",
    "gpt-6-astra.codex": "FAIL",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-090",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "FAIL",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "FAIL",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-091",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-092",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "claude-opus-5.5.v2": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4-pro.v2": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "deepseek-v4.1-flash.v2": "PASS",
    "gemma-4-31b": "FAIL",
    "gemma-4-31b.v2": "PASS",
    "glm-5.3": "FAIL",
    "glm-5.3.v2": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-6-astra.v2": "PASS",
    "gpt-oss-120b": "FAIL",
    "gpt-oss-120b.v2": "FAIL",
    "kimi-k3": "PASS",
    "kimi-k3.v2": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "mimo-v2.6-pro.v2": "PASS",
    "minimax-m3": "PASS",
    "minimax-m3.v2": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-2.4t.v2": "FAIL",
    "qwen-3.8-max": "PASS",
    "qwen-3.8-max.v2": "FAIL"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-093",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-094",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-095",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-096",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4.1-flash": "FAIL",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "FAIL",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "FAIL",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "FAIL",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-097",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "FAIL",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "FAIL",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "FAIL",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-098",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "claude-opus-5.5.v2": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4-pro.v2": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "deepseek-v4.1-flash.v2": "PASS",
    "gemma-4-31b.v2": "FAIL",
    "glm-5.3": "PASS",
    "glm-5.3.v2": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-6-astra.v2": "PASS",
    "gpt-oss-120b": "FAIL",
    "gpt-oss-120b.v2": "FAIL",
    "kimi-k3": "PASS",
    "kimi-k3.v2": "PASS",
    "mimo-v2.6-pro.v2": "PASS",
    "minimax-m3": "PASS",
    "minimax-m3.v2": "PASS",
    "qwen-3.8-2.4t.v2": "PASS",
    "qwen-3.8-max": "PASS",
    "qwen-3.8-max.v2": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-099",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "FAIL",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "FAIL",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "FAIL",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "FAIL"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-100",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "FAIL",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-101",
   "outcomes": {
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "FAIL",
    "gemma-4-31b": "PASS",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-102",
   "outcomes": {
    "claude-fable-5.1": "PASS",
    "claude-fable-5.1.cc": "PASS",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "deepseek-v4-pro": "PASS",
    "deepseek-v4.1-flash": "PASS",
    "gemma-4-31b": "FAIL",
    "glm-5.3": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-oss-120b": "FAIL",
    "kimi-k3": "PASS",
    "mimo-v2.6-pro": "PASS",
    "minimax-m3": "PASS",
    "qwen-3.8-2.4t": "PASS",
    "qwen-3.8-max": "PASS"
   },
   "tier": "tier-3"
  },
  {
   "id": "CASE-103",
   "outcomes": {
    "claude-fable-5.1": "FAIL",
    "claude-fable-5.1.cc": "FAIL",
    "claude-opus-5.5": "PASS",
    "claude-opus-5.5.cc": "PASS",
    "claude-opus-5.5.v2": "PASS",
    "deepseek-v4-pro": "FAIL",
    "deepseek-v4-pro.v2": "PASS",
    "deepseek-v4.1-flash": "FAIL",
    "deepseek-v4.1-flash.v2": "FAIL",
    "gemma-4-31b": "FAIL",
    "gemma-4-31b.v2": "FAIL",
    "glm-5.3": "PASS",
    "glm-5.3.v2": "PASS",
    "gpt-6-astra": "PASS",
    "gpt-6-astra.codex": "PASS",
    "gpt-6-astra.v2": "PASS",
    "gpt-oss-120b": "FAIL",
    "gpt-oss-120b.v2": "FAIL",
    "kimi-k3": "PASS",
    "kimi-k3.v2": "PASS",
    "mimo-v2.6-pro": "FAIL",
    "mimo-v2.6-pro.v2": "FAIL",
    "minimax-m3": "FAIL",
    "minimax-m3.v2": "FAIL",
    "qwen-3.8-2.4t.v2": "FAIL",
    "qwen-3.8-max": "PASS",
    "qwen-3.8-max.v2": "PASS"
   },
   "tier": "tier-3"
  }
 ],
 "configs": [
  {
   "harness": "neutral-v1",
   "name": "Claude Fable 5.1",
   "slug": "claude-fable-5.1",
   "status": "paused",
   "weights": "proprietary"
  },
  {
   "harness": "claude-code",
   "name": "Claude Fable 5.1",
   "slug": "claude-fable-5.1.cc",
   "status": "paused",
   "weights": "proprietary"
  },
  {
   "harness": "neutral-v1",
   "name": "Claude Opus 5.5",
   "slug": "claude-opus-5.5",
   "status": "ok",
   "weights": "proprietary"
  },
  {
   "harness": "claude-code",
   "name": "Claude Opus 5.5",
   "slug": "claude-opus-5.5.cc",
   "status": "ok",
   "weights": "proprietary"
  },
  {
   "harness": "neutral-v2",
   "name": "Claude Opus 5.5",
   "slug": "claude-opus-5.5.v2",
   "status": "ok",
   "weights": "proprietary"
  },
  {
   "harness": "neutral-v1",
   "name": "DeepSeek V4 Pro",
   "slug": "deepseek-v4-pro",
   "status": "ok",
   "weights": "open"
  },
  {
   "harness": "neutral-v2",
   "name": "DeepSeek V4 Pro",
   "slug": "deepseek-v4-pro.v2",
   "status": "ok",
   "weights": "open"
  },
  {
   "harness": "neutral-v1",
   "name": "DeepSeek V4.1 Flash",
   "slug": "deepseek-v4.1-flash",
   "status": "ok",
   "weights": "open"
  },
  {
   "harness": "neutral-v2",
   "name": "DeepSeek V4.1 Flash",
   "slug": "deepseek-v4.1-flash.v2",
   "status": "ok",
   "weights": "open"
  },
  {
   "harness": "neutral-v1",
   "name": "Gemma 4 31B",
   "slug": "gemma-4-31b",
   "status": "ok",
   "weights": "open"
  },
  {
   "harness": "neutral-v2",
   "name": "Gemma 4 31B",
   "slug": "gemma-4-31b.v2",
   "status": "ok",
   "weights": "open"
  },
  {
   "harness": "neutral-v1",
   "name": "GLM-5.3",
   "slug": "glm-5.3",
   "status": "ok",
   "weights": "open"
  },
  {
   "harness": "neutral-v2",
   "name": "GLM-5.3",
   "slug": "glm-5.3.v2",
   "status": "ok",
   "weights": "open"
  },
  {
   "harness": "neutral-v1",
   "name": "GPT-6 Astra",
   "slug": "gpt-6-astra",
   "status": "ok",
   "weights": "proprietary"
  },
  {
   "harness": "codex",
   "name": "GPT-6 Astra",
   "slug": "gpt-6-astra.codex",
   "status": "ok",
   "weights": "proprietary"
  },
  {
   "harness": "neutral-v2",
   "name": "GPT-6 Astra",
   "slug": "gpt-6-astra.v2",
   "status": "ok",
   "weights": "proprietary"
  },
  {
   "harness": "neutral-v1",
   "name": "gpt-oss-120b",
   "slug": "gpt-oss-120b",
   "status": "defect-format",
   "weights": "open"
  },
  {
   "harness": "neutral-v2",
   "name": "gpt-oss-120b",
   "slug": "gpt-oss-120b.v2",
   "status": "defect-format",
   "weights": "open"
  },
  {
   "harness": "neutral-v1",
   "name": "Kimi K3",
   "slug": "kimi-k3",
   "status": "ok",
   "weights": "open"
  },
  {
   "harness": "neutral-v2",
   "name": "Kimi K3",
   "slug": "kimi-k3.v2",
   "status": "ok",
   "weights": "open"
  },
  {
   "harness": "neutral-v1",
   "name": "MiMo V2.6 Pro",
   "slug": "mimo-v2.6-pro",
   "status": "ok",
   "weights": "open"
  },
  {
   "harness": "neutral-v2",
   "name": "MiMo V2.6 Pro",
   "slug": "mimo-v2.6-pro.v2",
   "status": "ok",
   "weights": "open"
  },
  {
   "harness": "neutral-v1",
   "name": "MiniMax M3",
   "slug": "minimax-m3",
   "status": "ok",
   "weights": "open"
  },
  {
   "harness": "neutral-v2",
   "name": "MiniMax M3",
   "slug": "minimax-m3.v2",
   "status": "ok",
   "weights": "open"
  },
  {
   "harness": "neutral-v1",
   "name": "Qwen 3.8 2.4T-A95B",
   "slug": "qwen-3.8-2.4t",
   "status": "ok",
   "weights": "open"
  },
  {
   "harness": "neutral-v2",
   "name": "Qwen 3.8 2.4T-A95B",
   "slug": "qwen-3.8-2.4t.v2",
   "status": "ok",
   "weights": "open"
  },
  {
   "harness": "neutral-v1",
   "name": "Qwen 3.8 Max",
   "slug": "qwen-3.8-max",
   "status": "ok",
   "weights": "open"
  },
  {
   "harness": "neutral-v2",
   "name": "Qwen 3.8 Max",
   "slug": "qwen-3.8-max.v2",
   "status": "ok",
   "weights": "open"
  }
 ],
 "counts": {
  "cases": 103,
  "configs": 28,
  "invalid_runs": 62,
  "pool": 106,
  "runs": 1546
 },
 "data_through": "2026-10-19",
 "economics": [
  {
   "config": "claude-opus-5.5.cc",
   "passes": 95,
   "runs": 103,
   "tok_in_per_pass": 1734800,
   "tok_out_per_pass": 700,
   "usd_per_pass_list": 7.6,
   "wall_s": 90
  },
  {
   "config": "gpt-6-astra",
   "passes": 95,
   "runs": 103,
   "tok_in_per_pass": 1017000,
   "tok_out_per_pass": 4200,
   "usd_per_pass_list": 11.0,
   "wall_s": 150
  },
  {
   "config": "claude-opus-5.5",
   "passes": 92,
   "runs": 103,
   "tok_in_per_pass": 823500,
   "tok_out_per_pass": 10200,
   "usd_per_pass_list": 4.2,
   "wall_s": 120
  },
  {
   "config": "kimi-k3",
   "passes": 92,
   "runs": 99,
   "tok_in_per_pass": 2105300,
   "tok_out_per_pass": 6600,
   "usd_per_pass_list": 6.3,
   "wall_s": 570
  },
  {
   "config": "glm-5.3",
   "passes": 90,
   "runs": 100,
   "tok_in_per_pass": 1448900,
   "tok_out_per_pass": 3600,
   "usd_per_pass_list": 0.16,
   "wall_s": 180
  },
  {
   "config": "gpt-6-astra.codex",
   "passes": 87,
   "runs": 103,
   "tok_in_per_pass": 170600,
   "tok_out_per_pass": 1700,
   "usd_per_pass_list": 2.2,
   "wall_s": 60
  },
  {
   "config": "deepseek-v4.1-flash",
   "passes": 85,
   "runs": 104,
   "tok_in_per_pass": 1958200,
   "tok_out_per_pass": 8500,
   "usd_per_pass_list": 0.43,
   "wall_s": 150
  },
  {
   "config": "deepseek-v4-pro",
   "passes": 82,
   "runs": 103,
   "tok_in_per_pass": 2201300,
   "tok_out_per_pass": 9700,
   "usd_per_pass_list": 4.4,
   "wall_s": 240
  },
  {
   "config": "qwen-3.8-2.4t",
   "passes": 80,
   "runs": 94,
   "tok_in_per_pass": 3528000,
   "tok_out_per_pass": 6400,
   "usd_per_pass_list": 8.4,
   "wall_s": 450
  },
  {
   "config": "minimax-m3",
   "passes": 77,
   "runs": 96,
   "tok_in_per_pass": 4789700,
   "tok_out_per_pass": 17900,
   "usd_per_pass_list": 1.9,
   "wall_s": 600
  },
  {
   "config": "qwen-3.8-max",
   "passes": 71,
   "runs": 94,
   "tok_in_per_pass": 2827800,
   "tok_out_per_pass": 7400,
   "usd_per_pass_list": null,
   "wall_s": 840
  },
  {
   "config": "mimo-v2.6-pro",
   "passes": 37,
   "runs": 90,
   "tok_in_per_pass": 1889000,
   "tok_out_per_pass": 4000,
   "usd_per_pass_list": null,
   "wall_s": 600
  },
  {
   "config": "claude-fable-5.1",
   "passes": 27,
   "runs": 28,
   "tok_in_per_pass": 2497800,
   "tok_out_per_pass": 28300,
   "usd_per_pass_list": 27.0,
   "wall_s": 360
  },
  {
   "config": "gemma-4-31b",
   "passes": 22,
   "runs": 91,
   "tok_in_per_pass": 755100,
   "tok_out_per_pass": 2500,
   "usd_per_pass_list": 0.89,
   "wall_s": 300
  },
  {
   "config": "claude-fable-5.1.cc",
   "passes": 19,
   "runs": 21,
   "tok_in_per_pass": 4644700,
   "tok_out_per_pass": 2000,
   "usd_per_pass_list": 55.0,
   "wall_s": 240
  },
  {
   "config": "gpt-6-astra.v2",
   "passes": 10,
   "runs": 10,
   "tok_in_per_pass": 1317700,
   "tok_out_per_pass": 6700,
   "usd_per_pass_list": 14.0,
   "wall_s": 180
  },
  {
   "config": "kimi-k3.v2",
   "passes": 10,
   "runs": 10,
   "tok_in_per_pass": 3286500,
   "tok_out_per_pass": 9800,
   "usd_per_pass_list": 9.5,
   "wall_s": 720
  },
  {
   "config": "claude-opus-5.5.v2",
   "passes": 10,
   "runs": 10,
   "tok_in_per_pass": 815300,
   "tok_out_per_pass": 7800,
   "usd_per_pass_list": 3.4,
   "wall_s": 150
  },
  {
   "config": "glm-5.3.v2",
   "passes": 9,
   "runs": 10,
   "tok_in_per_pass": 1833700,
   "tok_out_per_pass": 5200,
   "usd_per_pass_list": 0.18,
   "wall_s": 510
  },
  {
   "config": "deepseek-v4-pro.v2",
   "passes": 9,
   "runs": 10,
   "tok_in_per_pass": 7632400,
   "tok_out_per_pass": 29700,
   "usd_per_pass_list": 10.0,
   "wall_s": 510
  },
  {
   "config": "minimax-m3.v2",
   "passes": 9,
   "runs": 10,
   "tok_in_per_pass": 7417300,
   "tok_out_per_pass": 25800,
   "usd_per_pass_list": 2.4,
   "wall_s": 750
  },
  {
   "config": "deepseek-v4.1-flash.v2",
   "passes": 7,
   "runs": 10,
   "tok_in_per_pass": 1893400,
   "tok_out_per_pass": 10300,
   "usd_per_pass_list": 0.62,
   "wall_s": 210
  },
  {
   "config": "mimo-v2.6-pro.v2",
   "passes": 7,
   "runs": 10,
   "tok_in_per_pass": 2969200,
   "tok_out_per_pass": 7800,
   "usd_per_pass_list": null,
   "wall_s": 1770
  },
  {
   "config": "qwen-3.8-max.v2",
   "passes": 7,
   "runs": 10,
   "tok_in_per_pass": 3144200,
   "tok_out_per_pass": 9600,
   "usd_per_pass_list": null,
   "wall_s": 990
  },
  {
   "config": "qwen-3.8-2.4t.v2",
   "passes": 7,
   "runs": 10,
   "tok_in_per_pass": 4679500,
   "tok_out_per_pass": 8300,
   "usd_per_pass_list": 14.0,
   "wall_s": 990
  },
  {
   "config": "gemma-4-31b.v2",
   "passes": 1,
   "runs": 10,
   "tok_in_per_pass": null,
   "tok_out_per_pass": null,
   "usd_per_pass_list": null,
   "wall_s": null
  },
  {
   "config": "gpt-oss-120b.v2",
   "passes": 0,
   "runs": 10,
   "tok_in_per_pass": null,
   "tok_out_per_pass": null,
   "usd_per_pass_list": null,
   "wall_s": null
  },
  {
   "config": "gpt-oss-120b",
   "passes": 0,
   "runs": 99,
   "tok_in_per_pass": null,
   "tok_out_per_pass": null,
   "usd_per_pass_list": null,
   "wall_s": null
  }
 ],
 "harness_pairs": [
  {
   "model": "claude-opus-5.5",
   "native": "claude-code",
   "native_result": {
    "hi": 0.96,
    "lo": 0.854,
    "n": 103,
    "passes": 95,
    "preliminary": false,
    "rate": 0.922,
    "shown": true
   },
   "neutral": {
    "hi": 0.939,
    "lo": 0.819,
    "n": 103,
    "passes": 92,
    "preliminary": false,
    "rate": 0.893,
    "shown": true
   }
  },
  {
   "model": "gpt-6-astra",
   "native": "codex",
   "native_result": {
    "hi": 0.902,
    "lo": 0.762,
    "n": 103,
    "passes": 87,
    "preliminary": false,
    "rate": 0.845,
    "shown": true
   },
   "neutral": {
    "hi": 0.96,
    "lo": 0.854,
    "n": 103,
    "passes": 95,
    "preliminary": false,
    "rate": 0.922,
    "shown": true
   }
  },
  {
   "model": "claude-fable-5.1",
   "native": "claude-code",
   "native_result": {
    "hi": 0.972,
    "lo": 0.699,
    "n": 20,
    "passes": 18,
    "preliminary": false,
    "rate": 0.9,
    "shown": true
   },
   "neutral": {
    "hi": 0.991,
    "lo": 0.764,
    "n": 20,
    "passes": 19,
    "preliminary": false,
    "rate": 0.95,
    "shown": true
   }
  }
 ],
 "harnesses": [
  {
   "id": "claude-code",
   "label": "Claude Code (native)"
  },
  {
   "id": "codex",
   "label": "Codex CLI (native)"
  },
  {
   "id": "neutral-v1",
   "label": "OpenCode 1.19.3 (neutral)"
  },
  {
   "id": "neutral-v2",
   "label": "OpenCode 1.19.3 (neutral, v2 config)"
  }
 ],
 "license": "CC-BY-4.0",
 "reliability": [
  {
   "blocked_pct": 2.9,
   "config": "claude-opus-5.5.cc",
   "false_done_pct": 0.0,
   "refusals": 0,
   "runs": 103,
   "silent_pct": 0.0,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 1.0,
   "config": "gpt-6-astra",
   "false_done_pct": 1.0,
   "refusals": 3,
   "runs": 103,
   "silent_pct": 1.0,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 2.9,
   "config": "claude-opus-5.5",
   "false_done_pct": 0.0,
   "refusals": 3,
   "runs": 103,
   "silent_pct": 2.9,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 0.0,
   "config": "kimi-k3",
   "false_done_pct": 0.0,
   "refusals": 0,
   "runs": 99,
   "silent_pct": 4.0,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 2.0,
   "config": "glm-5.3",
   "false_done_pct": 0.0,
   "refusals": 0,
   "runs": 100,
   "silent_pct": 1.0,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 6.8,
   "config": "gpt-6-astra.codex",
   "false_done_pct": 0.0,
   "refusals": 0,
   "runs": 103,
   "silent_pct": 0.0,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 0.0,
   "config": "deepseek-v4.1-flash",
   "false_done_pct": 5.8,
   "refusals": 0,
   "runs": 104,
   "silent_pct": 13.5,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 8.7,
   "config": "deepseek-v4-pro",
   "false_done_pct": 2.9,
   "refusals": 0,
   "runs": 103,
   "silent_pct": 2.9,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 1.1,
   "config": "qwen-3.8-2.4t",
   "false_done_pct": 1.1,
   "refusals": 6,
   "runs": 94,
   "silent_pct": 9.6,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 3.1,
   "config": "minimax-m3",
   "false_done_pct": 0.0,
   "refusals": 4,
   "runs": 96,
   "silent_pct": 14.6,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 1.1,
   "config": "qwen-3.8-max",
   "false_done_pct": 1.1,
   "refusals": 0,
   "runs": 94,
   "silent_pct": 20.2,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 0.0,
   "config": "mimo-v2.6-pro",
   "false_done_pct": 2.2,
   "refusals": 5,
   "runs": 90,
   "silent_pct": 52.2,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 0.0,
   "config": "claude-fable-5.1",
   "false_done_pct": 3.6,
   "refusals": 1,
   "runs": 28,
   "silent_pct": 3.6,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 4.4,
   "config": "gemma-4-31b",
   "false_done_pct": 0.0,
   "refusals": 6,
   "runs": 91,
   "silent_pct": 27.5,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 4.8,
   "config": "claude-fable-5.1.cc",
   "false_done_pct": 0.0,
   "refusals": 0,
   "runs": 21,
   "silent_pct": 0.0,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 0.0,
   "config": "gpt-6-astra.v2",
   "false_done_pct": 0.0,
   "refusals": 0,
   "runs": 10,
   "silent_pct": 0.0,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 0.0,
   "config": "kimi-k3.v2",
   "false_done_pct": 0.0,
   "refusals": 0,
   "runs": 10,
   "silent_pct": 0.0,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 0.0,
   "config": "claude-opus-5.5.v2",
   "false_done_pct": 0.0,
   "refusals": 0,
   "runs": 10,
   "silent_pct": 0.0,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 0.0,
   "config": "glm-5.3.v2",
   "false_done_pct": 0.0,
   "refusals": 0,
   "runs": 10,
   "silent_pct": 10.0,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 0.0,
   "config": "deepseek-v4-pro.v2",
   "false_done_pct": 0.0,
   "refusals": 0,
   "runs": 10,
   "silent_pct": 10.0,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 0.0,
   "config": "minimax-m3.v2",
   "false_done_pct": 0.0,
   "refusals": 0,
   "runs": 10,
   "silent_pct": 10.0,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 10.0,
   "config": "deepseek-v4.1-flash.v2",
   "false_done_pct": 10.0,
   "refusals": 0,
   "runs": 10,
   "silent_pct": 20.0,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 0.0,
   "config": "mimo-v2.6-pro.v2",
   "false_done_pct": 0.0,
   "refusals": 0,
   "runs": 10,
   "silent_pct": 30.0,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 0.0,
   "config": "qwen-3.8-max.v2",
   "false_done_pct": 0.0,
   "refusals": 0,
   "runs": 10,
   "silent_pct": 30.0,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 10.0,
   "config": "qwen-3.8-2.4t.v2",
   "false_done_pct": 0.0,
   "refusals": 0,
   "runs": 10,
   "silent_pct": 20.0,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 10.0,
   "config": "gemma-4-31b.v2",
   "false_done_pct": 0.0,
   "refusals": 0,
   "runs": 10,
   "silent_pct": 30.0,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 0.0,
   "config": "gpt-oss-120b.v2",
   "false_done_pct": 0.0,
   "refusals": 0,
   "runs": 10,
   "silent_pct": 100.0,
   "tests_weakened_pct": 0.0
  },
  {
   "blocked_pct": 0.0,
   "config": "gpt-oss-120b",
   "false_done_pct": 1.0,
   "refusals": 4,
   "runs": 99,
   "silent_pct": 100.0,
   "tests_weakened_pct": 0.0
  }
 ],
 "schema": 1,
 "scoreboard": [
  {
   "config": "claude-opus-5.5.cc",
   "hi": 0.982,
   "lo": 0.793,
   "n": 31,
   "passes": 29,
   "preliminary": false,
   "rate": 0.935,
   "shown": true,
   "tier": "tier-1"
  },
  {
   "config": "claude-opus-5.5.cc",
   "hi": 0.98,
   "lo": 0.774,
   "n": 28,
   "passes": 26,
   "preliminary": false,
   "rate": 0.929,
   "shown": true,
   "tier": "tier-2"
  },
  {
   "config": "claude-opus-5.5.cc",
   "hi": 0.964,
   "lo": 0.788,
   "n": 44,
   "passes": 40,
   "preliminary": false,
   "rate": 0.909,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "gpt-6-astra",
   "hi": 0.967,
   "lo": 0.751,
   "n": 31,
   "passes": 28,
   "preliminary": false,
   "rate": 0.903,
   "shown": true,
   "tier": "tier-1"
  },
  {
   "config": "gpt-6-astra",
   "hi": 0.994,
   "lo": 0.823,
   "n": 28,
   "passes": 27,
   "preliminary": false,
   "rate": 0.964,
   "shown": true,
   "tier": "tier-2"
  },
  {
   "config": "gpt-6-astra",
   "hi": 0.964,
   "lo": 0.788,
   "n": 44,
   "passes": 40,
   "preliminary": false,
   "rate": 0.909,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "claude-opus-5.5",
   "hi": 0.982,
   "lo": 0.793,
   "n": 31,
   "passes": 29,
   "preliminary": false,
   "rate": 0.935,
   "shown": true,
   "tier": "tier-1"
  },
  {
   "config": "claude-opus-5.5",
   "hi": 0.994,
   "lo": 0.823,
   "n": 28,
   "passes": 27,
   "preliminary": false,
   "rate": 0.964,
   "shown": true,
   "tier": "tier-2"
  },
  {
   "config": "claude-opus-5.5",
   "hi": 0.905,
   "lo": 0.68,
   "n": 44,
   "passes": 36,
   "preliminary": false,
   "rate": 0.818,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "kimi-k3",
   "hi": 0.993,
   "lo": 0.811,
   "n": 26,
   "passes": 25,
   "preliminary": false,
   "rate": 0.962,
   "shown": true,
   "tier": "tier-1"
  },
  {
   "config": "kimi-k3",
   "hi": 0.943,
   "lo": 0.685,
   "n": 28,
   "passes": 24,
   "preliminary": false,
   "rate": 0.857,
   "shown": true,
   "tier": "tier-2"
  },
  {
   "config": "kimi-k3",
   "hi": 0.996,
   "lo": 0.882,
   "n": 44,
   "passes": 43,
   "preliminary": false,
   "rate": 0.977,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "glm-5.3",
   "hi": 0.993,
   "lo": 0.817,
   "n": 27,
   "passes": 26,
   "preliminary": false,
   "rate": 0.963,
   "shown": true,
   "tier": "tier-1"
  },
  {
   "config": "glm-5.3",
   "hi": 0.963,
   "lo": 0.728,
   "n": 28,
   "passes": 25,
   "preliminary": false,
   "rate": 0.893,
   "shown": true,
   "tier": "tier-2"
  },
  {
   "config": "glm-5.3",
   "hi": 0.95,
   "lo": 0.76,
   "n": 44,
   "passes": 39,
   "preliminary": false,
   "rate": 0.886,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "gpt-6-astra.codex",
   "hi": 0.908,
   "lo": 0.637,
   "n": 31,
   "passes": 25,
   "preliminary": false,
   "rate": 0.806,
   "shown": true,
   "tier": "tier-1"
  },
  {
   "config": "gpt-6-astra.codex",
   "hi": 0.994,
   "lo": 0.823,
   "n": 28,
   "passes": 27,
   "preliminary": false,
   "rate": 0.964,
   "shown": true,
   "tier": "tier-2"
  },
  {
   "config": "gpt-6-astra.codex",
   "hi": 0.888,
   "lo": 0.655,
   "n": 44,
   "passes": 35,
   "preliminary": false,
   "rate": 0.795,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "deepseek-v4.1-flash",
   "hi": 0.929,
   "lo": 0.674,
   "n": 31,
   "passes": 26,
   "preliminary": false,
   "rate": 0.839,
   "shown": true,
   "tier": "tier-1"
  },
  {
   "config": "deepseek-v4.1-flash",
   "hi": 0.943,
   "lo": 0.685,
   "n": 28,
   "passes": 24,
   "preliminary": false,
   "rate": 0.857,
   "shown": true,
   "tier": "tier-2"
  },
  {
   "config": "deepseek-v4.1-flash",
   "hi": 0.888,
   "lo": 0.655,
   "n": 44,
   "passes": 35,
   "preliminary": false,
   "rate": 0.795,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "deepseek-v4-pro",
   "hi": 0.947,
   "lo": 0.703,
   "n": 30,
   "passes": 26,
   "preliminary": false,
   "rate": 0.867,
   "shown": true,
   "tier": "tier-1"
  },
  {
   "config": "deepseek-v4-pro",
   "hi": 0.98,
   "lo": 0.774,
   "n": 28,
   "passes": 26,
   "preliminary": false,
   "rate": 0.929,
   "shown": true,
   "tier": "tier-2"
  },
  {
   "config": "deepseek-v4-pro",
   "hi": 0.781,
   "lo": 0.511,
   "n": 44,
   "passes": 29,
   "preliminary": false,
   "rate": 0.659,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "qwen-3.8-2.4t",
   "hi": 0.958,
   "lo": 0.7,
   "n": 25,
   "passes": 22,
   "preliminary": false,
   "rate": 0.88,
   "shown": true,
   "tier": "tier-1"
  },
  {
   "config": "qwen-3.8-2.4t",
   "hi": 0.98,
   "lo": 0.774,
   "n": 28,
   "passes": 26,
   "preliminary": false,
   "rate": 0.929,
   "shown": true,
   "tier": "tier-2"
  },
  {
   "config": "qwen-3.8-2.4t",
   "hi": 0.88,
   "lo": 0.633,
   "n": 41,
   "passes": 32,
   "preliminary": false,
   "rate": 0.78,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "minimax-m3",
   "hi": 0.936,
   "lo": 0.653,
   "n": 25,
   "passes": 21,
   "preliminary": false,
   "rate": 0.84,
   "shown": true,
   "tier": "tier-1"
  },
  {
   "config": "minimax-m3",
   "hi": 0.921,
   "lo": 0.644,
   "n": 28,
   "passes": 23,
   "preliminary": false,
   "rate": 0.821,
   "shown": true,
   "tier": "tier-2"
  },
  {
   "config": "minimax-m3",
   "hi": 0.868,
   "lo": 0.623,
   "n": 43,
   "passes": 33,
   "preliminary": false,
   "rate": 0.767,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "qwen-3.8-max",
   "hi": 0.923,
   "lo": 0.6,
   "n": 21,
   "passes": 17,
   "preliminary": false,
   "rate": 0.81,
   "shown": true,
   "tier": "tier-1"
  },
  {
   "config": "qwen-3.8-max",
   "hi": 0.898,
   "lo": 0.605,
   "n": 28,
   "passes": 22,
   "preliminary": false,
   "rate": 0.786,
   "shown": true,
   "tier": "tier-2"
  },
  {
   "config": "qwen-3.8-max",
   "hi": 0.837,
   "lo": 0.582,
   "n": 44,
   "passes": 32,
   "preliminary": false,
   "rate": 0.727,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "mimo-v2.6-pro",
   "hi": 0.819,
   "lo": 0.433,
   "n": 20,
   "passes": 13,
   "preliminary": false,
   "rate": 0.65,
   "shown": true,
   "tier": "tier-1"
  },
  {
   "config": "mimo-v2.6-pro",
   "hi": 0.705,
   "lo": 0.358,
   "n": 28,
   "passes": 15,
   "preliminary": false,
   "rate": 0.536,
   "shown": true,
   "tier": "tier-2"
  },
  {
   "config": "mimo-v2.6-pro",
   "hi": 0.359,
   "lo": 0.117,
   "n": 42,
   "passes": 9,
   "preliminary": false,
   "rate": 0.214,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "claude-fable-5.1",
   "n": 8,
   "preliminary": true,
   "shown": false,
   "tier": "tier-1"
  },
  {
   "config": "claude-fable-5.1",
   "hi": 0.991,
   "lo": 0.764,
   "n": 20,
   "passes": 19,
   "preliminary": false,
   "rate": 0.95,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "gemma-4-31b",
   "hi": 0.693,
   "lo": 0.307,
   "n": 22,
   "passes": 11,
   "preliminary": false,
   "rate": 0.5,
   "shown": true,
   "tier": "tier-1"
  },
  {
   "config": "gemma-4-31b",
   "hi": 0.315,
   "lo": 0.057,
   "n": 28,
   "passes": 4,
   "preliminary": false,
   "rate": 0.143,
   "shown": true,
   "tier": "tier-2"
  },
  {
   "config": "gemma-4-31b",
   "hi": 0.313,
   "lo": 0.085,
   "n": 41,
   "passes": 7,
   "preliminary": false,
   "rate": 0.171,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "claude-fable-5.1.cc",
   "hi": 0.973,
   "lo": 0.711,
   "n": 21,
   "passes": 19,
   "preliminary": false,
   "rate": 0.905,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "gpt-6-astra.v2",
   "hi": 1.0,
   "lo": 0.722,
   "n": 10,
   "passes": 10,
   "preliminary": true,
   "rate": 1.0,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "kimi-k3.v2",
   "hi": 1.0,
   "lo": 0.722,
   "n": 10,
   "passes": 10,
   "preliminary": true,
   "rate": 1.0,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "claude-opus-5.5.v2",
   "hi": 1.0,
   "lo": 0.722,
   "n": 10,
   "passes": 10,
   "preliminary": true,
   "rate": 1.0,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "glm-5.3.v2",
   "hi": 0.982,
   "lo": 0.596,
   "n": 10,
   "passes": 9,
   "preliminary": true,
   "rate": 0.9,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "deepseek-v4-pro.v2",
   "hi": 0.982,
   "lo": 0.596,
   "n": 10,
   "passes": 9,
   "preliminary": true,
   "rate": 0.9,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "minimax-m3.v2",
   "hi": 0.982,
   "lo": 0.596,
   "n": 10,
   "passes": 9,
   "preliminary": true,
   "rate": 0.9,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "deepseek-v4.1-flash.v2",
   "hi": 0.892,
   "lo": 0.397,
   "n": 10,
   "passes": 7,
   "preliminary": true,
   "rate": 0.7,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "mimo-v2.6-pro.v2",
   "hi": 0.892,
   "lo": 0.397,
   "n": 10,
   "passes": 7,
   "preliminary": true,
   "rate": 0.7,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "qwen-3.8-max.v2",
   "hi": 0.892,
   "lo": 0.397,
   "n": 10,
   "passes": 7,
   "preliminary": true,
   "rate": 0.7,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "qwen-3.8-2.4t.v2",
   "hi": 0.892,
   "lo": 0.397,
   "n": 10,
   "passes": 7,
   "preliminary": true,
   "rate": 0.7,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "gemma-4-31b.v2",
   "hi": 0.404,
   "lo": 0.018,
   "n": 10,
   "passes": 1,
   "preliminary": true,
   "rate": 0.1,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "gpt-oss-120b.v2",
   "hi": 0.278,
   "lo": 0.0,
   "n": 10,
   "passes": 0,
   "preliminary": true,
   "rate": 0.0,
   "shown": true,
   "tier": "tier-3"
  },
  {
   "config": "gpt-oss-120b",
   "hi": 0.121,
   "lo": 0.0,
   "n": 28,
   "passes": 0,
   "preliminary": false,
   "rate": 0.0,
   "shown": true,
   "tier": "tier-1"
  },
  {
   "config": "gpt-oss-120b",
   "hi": 0.121,
   "lo": 0.0,
   "n": 28,
   "passes": 0,
   "preliminary": false,
   "rate": 0.0,
   "shown": true,
   "tier": "tier-2"
  },
  {
   "config": "gpt-oss-120b",
   "hi": 0.082,
   "lo": 0.0,
   "n": 43,
   "passes": 0,
   "preliminary": false,
   "rate": 0.0,
   "shown": true,
   "tier": "tier-3"
  }
 ],
 "tiers": [
  {
   "id": "tier-1",
   "label": "Tier 1 (routine)"
  },
  {
   "id": "tier-2",
   "label": "Tier 2 (moderate)"
  },
  {
   "id": "tier-3",
   "label": "Tier 3 (hard)"
  }
 ]
}
