Modality: llm_chat · full deep dive — every ranked model, test result, and artifact.
Ranked by confidence-adjusted score (single/zero-sample, non-curated scores floored; curated empirical scores trusted as-is).
| # | Model | Provider | Adj. Score | Raw | Evidence |
|---|---|---|---|---|---|
| 1 | gpt-4o | openai | 0.995 | 1.000 | n=977 |
| 2 | deepseek-chat | deepseek | 0.556 | 0.556 | n=17551 |
| 3 | gpt-5.5::think=fast | codex | 0.525 | 0.963 | n=6 |
| 4 | gpt-5.5::think=deep | codex | 0.525 | 0.963 | n=6 |
| 5 | claude-haiku-4-5-20251001 | anthropic | 0.426 | 0.426 | n=13591 |
| 6 | gpt-5.4::think=fast | codex | 0.334 | 0.612 | n=6 |
| 7 | gpt-5.4::think=deep | codex | 0.334 | 0.612 | n=6 |
| 8 | codex-auto-review | codex | 0.286 | 0.525 | n=6 |
| 9 | gemini-2.5-flash | google_gemini | 0.063 | 0.063 | n=8321 |
| 10 | gpt-5.4 | codex | 0.000 | 0.000 | n=50 |
| 11 | gpt-5.5 | codex | 0.000 | 0.000 | n=50 |
No benchmark outputs recorded for this niche yet.