FuseChat-Qwen-2.5-7B-Instruct: benchmark results
FuseAI's FuseChat-3.0 knowledge-fusion tune of Qwen2.5-7B-Instruct, distilling strengths of larger source LLMs via SFT and DPO. Provider: FuseAI. Released 2024-11-12. Access: Open.
Unified ELO 1587 ± 1, rank #337 of 1553 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MATH Level 5 | 45.62 | Score | 93.8 |
| AlpacaEval 2.0 | 63.58 | LC Win Rate (%) | 93.7 |
| Open LLM Leaderboard - MMLU-Pro | 34.65 | Score | 74.9 |
| Open LLM Leaderboard - BBH | 36.25 | Score | 74.2 |
| Open LLM Leaderboard - IFEval | 59.06 | Score | 70.8 |
| Open LLM Leaderboard - GPQA | 6.15 | Score | 51.6 |
| Open LLM Leaderboard - MuSR | 6.72 | Score | 31.9 |
Interactive version: theaggregate.ai/model?slug=fusechat-qwen-2-5-7b-instruct · How It Works · Data refreshed daily, snapshot 2026-09-08.