Qwen 2.5 Turbo: benchmark results
Alibaba's fast, low-cost proprietary Qwen2.5 API tier, whose Turbo update (November 2024) extended context to 1M tokens via sparse attention. Provider: Alibaba. Released 2024-09-19. Access: API.
Aggregate Rating 1464 ± 24, rank #3071 of 10916 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BenchTable - Tech | 37.5 | Weighted Score (%) | 32 |
| AI Chess Leaderboard (Reasoning) | 574 | Elo | 27.1 |
| AA MMLU-Pro | 63.31 | Accuracy (%) | 24.7 |
| BenchTable - Reasoning | 16.9 | Weighted Score (%) | 20.9 |
| AI Chess Leaderboard (Continuation) | 438 | Elo | 20.4 |
| BenchTable | 25.1 | Total Score (%) | 20.3 |
| BenchTable - STEM | 21.3 | Weighted Score (%) | 17.9 |
| AA LiveCodeBench | 16.3 | Pass@1 (%) | 17 |
| AA GPQA Diamond | 41.01 | Accuracy (%) | 15.9 |
| AA Humanity's Last Exam | 4.09 | Accuracy (%) | 13.5 |
| BenchTable - Utility | 16.3 | Weighted Score (%) | 7.7 |
| ResearchCodeBench | 8.02 | Task Success Rate (%) | 3.2 |
Interactive version: theaggregate.ai/model?slug=qwen-2-5-turbo · How It Works · Data refreshed daily, snapshot 2026-11-08.