Qwen2.5-Math-1.5B-Instruct: benchmark results
Alibaba's Qwen2.5-Math-1.5B-Instruct, the instruction-tuned version of Qwen2.5-Math-1.5B for solving English and Chinese math problems via chain-of-thought and tool-integrated reasoning. Provider: Alibaba. Released 2024-09-19. Access: Open.
Aggregate Rating 1268 ± 31, rank #1522 of 1656 rated models, from 31 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MATH Level 5 | 26.28 | Score | 79.2 |
| MERA - ruHumanEval | 15.98 | pass@1 (%) | 57.9 |
| MERA - ruCodeEval | 15.12 | pass@1 (%) | 57.6 |
| MERA - LCS | 13 | Accuracy (%) | 51 |
| MERA - ruMultiAr | 30.08 | EM (%) | 47.1 |
| MERA - ruModAr | 49.53 | EM (%) | 39.1 |
| MERA - SimpleAr | 95.3 | EM (%) | 37.1 |
| Open LLM Leaderboard - MuSR | 36.85 | Score | 23 |
| MERA - RWSD | 50.38 | Accuracy (%) | 22.1 |
| MERA - MathLogicQA | 34.91 | Accuracy (%) | 21.9 |
| Open LLM Leaderboard - BBH | 37.52 | Score | 21.6 |
| ReliableMath - Prudence | 0 | Score (%) | 21.1 |
Interactive version: theaggregate.ai/model?slug=qwen2-5-math-1-5b-instruct · How It Works · Data refreshed daily, snapshot 2026-10-20.