Qwen·released 2026-08-141 source
Qwen 3.8 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 87.5 on ARC-AGI (unverified)·0 of 7 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| ARC-AGI | 87.5accuracy (%) | unverifiedT1 | 2026-08-14https://arcprize.org/leaderboard |
| DTBench | 80accuracy (%) | unverifiedT1 | 2026-08-14https://conceptualreasoning.ai/dtbench |
| LMCA | 48.66accuracy (%) | unverifiedT1 | 2026-08-14https://conceptualreasoning.ai/lmca |
| APEX-Agents | 47.5accuracy (%) | unverifiedT2 | 2026-08-14 |
| Surface Evolver Bench | 45accuracy (%) | unverifiedT1 | 2026-08-14https://yhenon.github.io/surface-evolver-llm-eval/ |
| ARC-AGI-2 | 42.36accuracy (%) | unverifiedT2 | 2026-08-14 |
| ProofBench | 16accuracy (%) | unverifiedT1 | 2026-08-14https://www.vals.ai/benchmarks/proof_bench |
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 7 tracked benchmarks and currently leads 0 of them. The record’s evidence status is unverified.
3 cited facts
Its mean gap to the best recorded score across its tracked benchmarks is 40.34 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 27B is an AI model developed by Qwen, released 2026-08-14. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Qwen 3.8 27B has recorded scores on 7 benchmarks, each shown with its evidence status.
Qwen 3.8 27B has recorded scores on 7 benchmarks — DTBench, LMCA, ARC-AGI, ARC-AGI-2, APEX-Agents, Surface Evolver Bench, 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.
Qwen 3.8 27B has 7 tracked claims: 7 unverified.