Qwen·released 2026-07-271 source
Qwen3.7 Flash benchmark scores: 5 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 5 benchmarks·best result 86.65 on OTIS Mock AIME 2024-2025 (unverified)·0 of 5 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.65accuracy (%) | unverifiedT2 | 2026-07-27 |
| GPQA diamond | 76.43accuracy (%) | unverifiedT2 | 2026-07-27 |
| FrontierMath-Tiers-1-3-v2-Private | 19.3accuracy (%) | unverifiedT2 | 2026-07-27 |
| Chess Puzzles | 18.98accuracy (%) | unverifiedT2 | 2026-07-27 |
| Mystery Game Puzzles | 6.37accuracy (%) | unverifiedT2 | 2026-07-27 |
Claims drawn from cited facts, not live model generation.
This model originates from Qwen and arrives in 2026, placing it in a recent generation of the developer's lineup. Because its parameter count is not specified here, the vintage and lineage are what define its standing, rather than any stated scale of the model itself.
4 cited facts
This model is scored on 5 tracked benchmarks. It holds no current top score on any of them. Its results remain unverified, as no independent evaluation has confirmed or disputed them.
3 cited facts
Its mean gap to the best recorded score across its tracked benchmarks is 47.23 points.
1 cited fact
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
Qwen3.7 Flash is an AI model developed by Qwen, released 2026-07-27. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Qwen3.7 Flash has recorded scores on 5 benchmarks, each shown with its evidence status.
Qwen3.7 Flash has recorded scores on 5 benchmarks — GPQA diamond, OTIS Mock AIME 2024-2025, Chess Puzzles, FrontierMath-Tiers-1-3-v2-Private, Mystery Game Puzzles. The full table above shows each score with its evidence status.
0 of 5 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
Qwen3.7 Flash has 5 tracked claims: 5 unverified.