Qwen·released 2026-08-021 source
Qwen 3.8 Max benchmark scores: 13 benchmarks tracked. 38% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 13 benchmarks·best result 99.44 on OTIS Mock AIME 2024-2025 (reproduced)·5 of 13 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 99.44accuracy (%) | reproduced· optimizedT1 | 2026-08-02Epoch AI |
| GPQA diamond | 90.24accuracy (%) | reproduced· optimizedT1 | 2026-08-02Epoch AI |
| DTBench | 86.67accuracy (%) | unverifiedT1 | 2026-08-02https://conceptualreasoning.ai/dtbench |
| FrontierMath-Tiers-1-3-v2-Private | 74.74accuracy (%) | reproducedT1 | 2026-08-02Epoch AI |
| APEX-Agents | 63.3accuracy (%) | unverifiedT2 | 2026-08-02 |
| ProofBench | 58accuracy (%) | unverifiedT1 | 2026-08-02https://www.vals.ai/benchmarks/proof_bench |
| DeepSWE | 57.46accuracy (%) | unverifiedT1 | 2026-08-02https://deepswe.datacurve.ai/ |
| LMCA | 54.4accuracy (%) | unverifiedT1 | 2026-08-02https://conceptualreasoning.ai/lmca |
| FrontierMath-Tier-4-v2-Private | 46.34accuracy (%) | reproducedT1 | 2026-08-02Epoch AI |
| SimpleQA Verified | 45.8accuracy (%) | unverifiedT2 | 2026-08-02 |
| Chess Puzzles | 43.18accuracy (%) | unverifiedT2 | 2026-08-02 |
| Mystery Game Puzzles | 31.7accuracy (%) | reproducedT1 | 2026-08-02Epoch AI |
| FrontierSWE | 15.81accuracy (%) | unverifiedT1 | 2026-08-02https://www.frontierswe.com/ |
Claims drawn from cited facts, not live model generation.
This model was developed by Qwen and released in 2026.
2 cited facts
This model has scores on 13 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 27.18 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
Qwen 3.8 Max is an AI model developed by Qwen, released 2026-08-02. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Qwen 3.8 Max has recorded scores on 13 benchmarks, each shown with its evidence status.
Qwen 3.8 Max has recorded scores on 13 benchmarks — GPQA diamond, OTIS Mock AIME 2024-2025, DTBench, LMCA, SimpleQA Verified, Chess Puzzles, and 7 more. The full table above shows each score with its evidence status.
5 of 13 recorded scores (38%) are independently reproduced rather than self-reported by the lab.
Qwen 3.8 Max has 13 tracked claims: 5 independently reproduced, 8 unverified.