Qwen 2.5 7B Instruct Turbo: benchmark results
Provider: Alibaba. Released 2024-09-19. Access: Open.
Unified ELO 1534 ± 1, rank #520 of 1392 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Enkrypt AI - Safety Risk | 17.33 | Risk Score | 93.5 |
| Enkrypt AI - Bias Risk | 50.65 | Risk Score | 92.4 |
| OpenEval - Omni-MATH | 29.4 | Accuracy (%) | 76.2 |
| Judge Arena | 1280 | ELO Score | 70.4 |
| OpenEval - MMLU-Pro CoT | 53.9 | CoT Correctness (%) | 69.6 |
| OpenEval - GPQA CoT | 34.08 | CoT Correctness (%) | 68.2 |
| OpenEval - IFEval Strict | 74.09 | Strict Accuracy (%) | 60.9 |
| Enkrypt AI - Risk Score | 33 | Risk Score | 47.7 |
| Enkrypt AI - Toxicity Risk | 4.36 | Risk Score | 41 |
| Enkrypt AI - Insecure Code Risk | 42.67 | Risk Score | 33 |
| Enkrypt AI - Jailbreak Risk | 14.21 | Risk Score | 24.4 |
| Vals AI LegalBench | 69.56 | Accuracy (%) | 14.9 |
Interactive version: theaggregate.ai/model?slug=qwen-2-5-7b-instruct-turbo · How It Works · Data refreshed daily, snapshot 2026-09-05.