IyawoBench: leaderboard
Metric: Three-way triage accuracy (%) over the 200 IyawoBench v1.0 vignettes (100 refer now, 60 refer today, 40 treat here), a triage decision with a one-sentence rationale at temperature 0; higher is better. Source: arxiv.org. Saturation forecast: Around May 2027. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.3 70B Instruct | 68 |
| 2 | Claude Sonnet 4.6 | 63 |
| 3 | Llama 3.1 8B Instruct | 46 |
Interactive version: theaggregate.ai/benchmark?slug=iyawobench · How It Works · Data refreshed daily, snapshot 2026-09-29.