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 | claude-sonnet-4-6 | claude_desktop | 0.773 | 0.850 | n=50 |
| 2 | deepseek-chat | deepseek | 0.706 | 1.000 | n=12 |
| 3 | gpt-4o | openai | 0.695 | 0.698 | n=1063 |
| 4 | claude-sonnet-4-6::think=fast | claude_code | 0.545 | 1.000 | n=6 |
| 5 | claude-sonnet-4-6::think=deep | claude_code | 0.545 | 1.000 | n=6 |
| 6 | gpt-5.5::think=deep | codex | 0.525 | 0.963 | n=6 |
| 7 | gpt-5.5::think=fast | codex | 0.525 | 0.963 | n=6 |
| 8 | claude-opus-4-7::think=fast | claude_code | 0.477 | 0.875 | n=6 |
| 9 | claude-opus-4-7::think=deep | claude_code | 0.477 | 0.875 | n=6 |
| 10 | gemini-2.5-pro | google_gemini | 0.444 | 1.000 | n=4 |
| 11 | claude-opus-4-8::think=fast | claude_code | 0.430 | 0.788 | n=6 |
| 12 | gpt-5.3-codex-spark::think=deep | codex | 0.382 | 0.700 | n=6 |
| 13 | claude-opus-4-8::think=deep | claude_code | 0.382 | 0.700 | n=6 |
| 14 | gpt-5.4::think=fast | codex | 0.334 | 0.612 | n=6 |
| 15 | gpt-5.4::think=deep | codex | 0.334 | 0.612 | n=6 |
| 16 | codex-auto-review | codex | 0.286 | 0.525 | n=6 |
| 17 | gpt-5.3-codex-spark::think=fast | codex | 0.286 | 0.525 | n=6 |
| 18 | claude-haiku-4-5-20251001 | anthropic | 0.212 | 0.424 | n=5 |
| 19 | gpt-5.4 | codex | 0.150 | 1.000 | provisional (n≤1) |
| 20 | gpt-5.5 | codex | 0.150 | 1.000 | provisional (n≤1) |
| 21 | claude-sonnet-4-5-20250929 | claude_code | 0.126 | 0.842 | provisional (n≤1) |
| 22 | gemini-3.1-pro | gemini | 0.120 | 0.800 | provisional (n≤1) |
| 23 | claude-opus-4-1-20250805 | claude_code | 0.111 | 0.743 | provisional (n≤1) |
| 24 | claude-opus-4-6 | claude_code | 0.107 | 0.715 | provisional (n≤1) |
| 25 | claude-opus-4-20250514 | claude_code | 0.099 | 0.659 | provisional (n≤1) |
| 26 | claude-opus-4-5-20251101 | claude_code | 0.097 | 0.650 | provisional (n≤1) |
| 27 | claude-sonnet-4-20250514 | claude_code | 0.096 | 0.643 | provisional (n≤1) |
| 28 | claude-opus-4-8 | claude_code | 0.071 | 0.472 | provisional (n≤1) |
| 29 | gemini-2.5-flash | google_gemini | 0.059 | 0.133 | n=4 |
| 30 | gpt-5.3-codex-spark | codex | 0.043 | 0.286 | provisional (n≤1) |
| 31 | claude-sonnet-4-6 | claude_code | 0.035 | 0.233 | provisional (n≤1) |
| 32 | claude-opus-4-7 | claude_code | 0.022 | 0.148 | provisional (n≤1) |
| 33 | claude-haiku-4-5-20251001 | claude_code | 0.000 | 0.000 | n=50 |
No benchmark outputs recorded for this niche yet.