Qwen Turbo: benchmark results
Alibaba Cloud's Qwen Turbo, a faster, shorter-context budget tier in the Qwen API line, positioned between Qwen-Max and Qwen-Flash, with tool calling and structured JSON output. Provider: Alibaba. Released 2024-09-19. Access: API.
Aggregate Rating 1526 ± 18, rank #699 of 1656 rated models, from 123 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ClinicalMC (English) | 49.68 | Mean of 11 task scores (%; triage accuracy, examination reca | 95 |
| AGC-Bench - schnovel | 1.35 | Dataset z-score | 92.1 |
| AGC-Bench - grapheval_ai_researcher | 0.97 | Dataset z-score | 91.4 |
| AGC-Bench - munch | 0.98 | Dataset z-score | 90.9 |
| AGC-Bench - proparalogy | 0.79 | Dataset z-score | 87.7 |
| Software Engineering Arena - Model Arena | 1002 | Elo Rating | 86.4 |
| MERA - BPS | 99.5 | Accuracy (%) | 85.7 |
| AGC-Bench - chinese_homophonic_puns | 0.99 | Dataset z-score | 85.2 |
| MERA - ruHumanEval | 48.6 | pass@1 (%) | 85.2 |
| AGC-Bench - permpst | 0.8 | Dataset z-score | 80.5 |
| AGC-Bench - simile_generation | 0.66 | Dataset z-score | 80 |
| AGC-Bench - humor_transfer | 0.88 | Dataset z-score | 77.2 |
Interactive version: theaggregate.ai/model?slug=qwen-turbo · How It Works · Data refreshed daily, snapshot 2026-10-20.