Qwen·released 2026-04-221 source
Qwen3.6 27B benchmark scores: 7 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 7 benchmarks·best result 91.1 on OTIS Mock AIME 2024-2025 (unverified)·0 of 7 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 91.1accuracy (%) | unverifiedT2 | 2026-04-22 |
| GPQA diamond | 81.14accuracy (%) | unverifiedT2 | 2026-04-22 |
| DTBench | 63.55accuracy (%) | unverifiedT1 | 2026-04-22https://conceptualreasoning.ai/dtbench |
| LMCA | 40.62accuracy (%) | unverifiedT1 | 2026-04-22https://conceptualreasoning.ai/lmca |
| FrontierMath-Tiers-1-3-v2-Private | 35.09accuracy (%) | unverifiedT2 | 2026-04-22 |
| Chess Puzzles | 17.93accuracy (%) | unverifiedT2 | 2026-04-22 |
| Mystery Game Puzzles | 0accuracy (%) | unverifiedT2 | 2026-04-22 |
Claims drawn from cited facts, not live model generation.
This model is developed by Qwen and was released in 2026, making it a recent-vintage entry in the developer's lineup. No parameter count is offered for this model, so its scale cannot be stated here — its origin with Qwen and its 2026 release are the only grounded details, and any claim about size or cost trade-offs would be unsupported.
4 cited facts
This model is tracked on 7 benchmarks, but it holds no current top score on any of them. Its record carries an unverified status: outside evaluation has neither confirmed nor disputed these numbers, so they should be read as neither proven nor challenged.
3 cited facts
On average, this model trails the best reported score on its benchmarks by 40.47 points, a wide gap under the disclosed harness that reads as well behind the leaders rather than at the frontier. It holds the top score on 0 benchmarks, meaning there is no evidence of category leadership here.
2 cited facts
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
Qwen3.6 27B is an AI model developed by Qwen, released 2026-04-22. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Qwen3.6 27B has recorded scores on 7 benchmarks, each shown with its evidence status.
Qwen3.6 27B has recorded scores on 7 benchmarks — GPQA diamond, OTIS Mock AIME 2024-2025, DTBench, LMCA, Chess Puzzles, FrontierMath-Tiers-1-3-v2-Private, and 1 more. The full table above shows each score with its evidence status.
0 of 7 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
Qwen3.6 27B has 7 tracked claims: 7 unverified.