Qwen 3.7 Flash: benchmark results
Provider: Alibaba. Released 2026-07-25. Access: API.
Unified ELO 1635 ± 1, rank #165 of 1392 rated models, from 40 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MERA v2 - SAGE | 68.2 | Score (%) | 91.7 |
| AI for Education Pedagogy - Science | 91.26 | Accuracy (%) | 85.5 |
| MERA v2 - GorillaHard | 50.6 | Score (%) | 76.4 |
| AI Chess Leaderboard (Reasoning) | 943 | Elo | 75.5 |
| OTIS Mock AIME 2024-25 | 86.67 | Accuracy (%) | 73.6 |
| AI for Education Pedagogy - Primary | 88.73 | Accuracy (%) | 71.4 |
| AI for Education Pedagogy - Secondary | 84.75 | Accuracy (%) | 71.4 |
| AI for Education Pedagogy - Social studies | 83.64 | Accuracy (%) | 71.4 |
| AI for Education Pedagogy - Maths | 84.92 | Accuracy (%) | 71.2 |
| Chess Puzzles (Epoch AI) | 23 | Accuracy (%) | 69.6 |
| AI for Education Pedagogy | 84.76 | Accuracy (%) | 68.7 |
| MERA v2 | 0.41 | Total score | 63.9 |
Interactive version: theaggregate.ai/model?slug=qwen-3-7-flash · How It Works · Data refreshed daily, snapshot 2026-09-05.