evals.report
BenchmarksLabsCompareRun guidesIn the wild

Qwen3.8-27B

Alibaba / Qwen · Qwen. Released Aug 5, 2026.

Qwen3.8-27B is a model from Alibaba / Qwen in the Qwen family, released Aug 5, 2026. evals.report tracks 4 reported Qwen3.8-27B benchmark scores across AA-Omniscience: Knowledge and Hallucination Benchmark, OSWorld, Terminal-Bench 2.1, IFBench — each shown with its benchmark, metric, source status, and date, and never combined into a single ranking.

4 results

Benchmark results 4

Compare this model
BenchmarkCategoryScoreMetricStatusDate
AA-Omniscience: Knowledge and Hallucination BenchmarkReasoning-10AA-Omniscience IndexOfficialAug 5, 2026Details
OSWorldAgents84.3%task success rateVerifiedAug 5, 2026Details
Terminal-Bench 2.1Agents73.0%task successVerifiedAug 5, 2026Details
IFBenchReasoning79.5%accuracyVerifiedAug 5, 2026Details