Qwen2.5-Math-1.5B-Instruct: benchmark results
Provider: Alibaba. Released 2024-09-16. Access: Open.
Unified ELO 1305 ± 1, rank #1342 of 1392 rated models, from 31 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MATH Level 5 | 26.28 | Score | 79.1 |
| MERA - ruHumanEval | 15.98 | pass@1 (%) | 57.7 |
| MERA - ruCodeEval | 15.12 | pass@1 (%) | 57.4 |
| MERA - LCS | 13 | Accuracy (%) | 51.2 |
| MERA - ruMultiAr | 30.08 | EM (%) | 46.9 |
| MERA - ruModAr | 49.53 | EM (%) | 39 |
| MERA - SimpleAr | 95.3 | EM (%) | 37 |
| MERA - RWSD | 50.38 | Accuracy (%) | 21.8 |
| Open LLM Leaderboard - BBH | 12.86 | Score | 21.7 |
| MERA - MathLogicQA | 34.91 | Accuracy (%) | 21.5 |
| ReliableMath - Prudence | 0 | Score (%) | 21.1 |
| Open LLM Leaderboard - MMLU-Pro | 8.9 | Score | 19.5 |
Interactive version: theaggregate.ai/model?slug=qwen2-5-math-1-5b-instruct · How It Works · Data refreshed daily, snapshot 2026-09-05.