Qwen·released 2026-02-251 source
Qwen 3.5 Flash (hosted 35B-A3B) benchmark scores: 9 benchmarks tracked. 33% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 9 benchmarks·best result 84.43 on OTIS Mock AIME 2024-2025 (reproduced)·3 of 9 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 84.43accuracy (%) | reproduced· optimizedT1 | 2026-02-25Epoch AI |
| GPQA diamond | 76.43accuracy (%) | reproduced· optimizedT1 | 2026-02-25Epoch AI |
| DTBench | 71.55accuracy (%) | unverifiedT1 | 2026-02-25https://conceptualreasoning.ai/dtbench |
| LMCA | 34.28accuracy (%) | unverifiedT1 | 2026-02-25https://conceptualreasoning.ai/lmca |
| SimpleQA Verified | 20.32accuracy (%) | unverifiedT2 | 2026-02-25 |
| FrontierMath-Tiers-1-3-v2-Private | 18.25accuracy (%) | unverifiedT2 | 2026-02-25 |
| Mystery Game Puzzles | 11.87accuracy (%) | unverifiedT2 | 2026-02-25 |
| Chess Puzzles | 9.51accuracy (%) | unverifiedT2 | 2026-02-25 |
| FrontierMath-Tier-4-2025-07-01-Private | 0accuracy (%) | reproducedT1 | 2026-02-25Epoch AI |
Claims drawn from cited facts, not live model generation.
This model was developed by Qwen and released in 2026. Its recorded parameter count is 35.0 billion.
3 cited facts
This model has scores on 9 tracked benchmarks and currently leads 0 of them. The record’s evidence status is independently reproduced.
3 cited facts
Its mean gap to the best recorded score across its tracked benchmarks is 44.78 points.
1 cited fact
2 facts cross-checked across data sources: 2 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: curated_param_counts, epoch_benchmarks
Qwen 3.5 Flash (hosted 35B-A3B) is an AI model developed by Qwen, released 2026-02-25. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Qwen 3.5 Flash (hosted 35B-A3B) has recorded scores on 9 benchmarks, each shown with its evidence status.
Qwen 3.5 Flash (hosted 35B-A3B) has recorded scores on 9 benchmarks — GPQA diamond, OTIS Mock AIME 2024-2025, DTBench, LMCA, SimpleQA Verified, Chess Puzzles, and 3 more. The full table above shows each score with its evidence status.
3 of 9 recorded scores (33%) are independently reproduced rather than self-reported by the lab.
Qwen 3.5 Flash (hosted 35B-A3B) has 9 tracked claims: 3 independently reproduced, 6 unverified.