PrismML Bonsai 2 27B - XHigh - MATH-500: leaderboard
PrismML’s comparison of Bonsai 2 27B and separately identified Qwen models at xhigh reasoning effort on 500 mathematics problems. Numeric-equivalence accuracy (%).
Metric: Numeric-equivalence accuracy (%). Source: raw.githubusercontent.com. Saturation forecast: Around January 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.8 27B (xHigh) | 99.8 | #116 (Qwen 3.8 27B) |
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-2-27b-xhigh-math-500 · How It Works · Data refreshed daily, snapshot 2026-10-29.