evals.report
BenchmarksLabsCompareRun guidesIn the wild

Qwen3.8 Max

Alibaba / Qwen · Qwen. Released Aug 3, 2026.

Qwen3.8 Max is a model from Alibaba / Qwen in the Qwen family, released Aug 3, 2026. evals.report tracks 6 reported Qwen3.8 Max benchmark scores across AA-Omniscience: Knowledge and Hallucination Benchmark, Terminal-Bench 2.1, SWE-bench Pro, OSWorld, MMMU-Pro, IFBench — each shown with its benchmark, metric, source status, and date, and never combined into a single ranking.

6 results

Benchmark results 6

Compare this model
BenchmarkCategoryScoreMetricStatusDate
AA-Omniscience: Knowledge and Hallucination BenchmarkReasoning4AA-Omniscience IndexOfficialAug 3, 2026Details
Terminal-Bench 2.1Agents86.6%task successVerifiedAug 3, 2026Details
SWE-bench ProCoding67.7%% resolvedVerifiedAug 3, 2026Details
OSWorldAgents86.1%task success rateVerifiedAug 3, 2026Details
MMMU-ProMultimodal82.3%accuracyVerifiedAug 3, 2026Details
IFBenchReasoning82.8%accuracyVerifiedAug 3, 2026Details