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-haiku-4-5-20251001 | anthropic | 0.150 | 1.000 | provisional (n≤1) |
| 2 | gpt-4o-mini | openai | 0.120 | 0.800 | provisional (n≤1) |
| 3 | gemini-2.5-flash | google_gemini | 0.090 | 0.600 | provisional (n≤1) |
No benchmark outputs recorded for this niche yet.