PrismML Bonsai 2 Small - MuSR: leaderboard
PrismML’s comparison of small Bonsai 2 and Qwen3.5 models on multi-step reasoning on the MuSR benchmark. Models use thinking with the same evaluation harness and sampling settings; the published scores are percentages.
Metric: Reported MuSR score (%). Source: raw.githubusercontent.com. Saturation forecast: Around January 2028. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.5 9B | 66.67 | #387 |
| 2 | Qwen 3.5 2B | 62.83 | #1146 |
| 3 | Qwen 3.5 4B | 62.43 | #496 |
| 4 | Qwen 3.5 0.8B | 58.2 | #1421 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=prismml-bonsai-2-small-musr · How It Works · Data refreshed daily, snapshot 2026-10-29.