evals.report
BenchmarksLabsCompareRun guidesIn the wild
Alibaba / QwenQwen

Qwen 3.6 Plus

Alibaba / Qwen · Qwen. Released Apr 2, 2026.

Qwen 3.6 Plus is a model from Alibaba / Qwen in the Qwen family, released Apr 2, 2026. evals.report tracks 19 reported Qwen 3.6 Plus benchmark scores across GPQA Diamond, AIME (OTIS Mock), SimpleQA Verified, SWE-bench Verified, FrontierMath, DeepSWE, LMArena, Artificial Analysis Intelligence Index, and 11 more — each shown with its benchmark, metric, source status, and date, and never combined into a single ranking.

19 results

Benchmark results 19

Compare this model
BenchmarkCategoryScoreMetricStatusDate
GPQA DiamondReasoning87.4%accuracyOfficialApr 2, 2026Details
AIME (OTIS Mock)Reasoning90.6%accuracyOfficialApr 2, 2026Details
SimpleQA VerifiedOther49.1%accuracyOfficialApr 2, 2026Details
SWE-bench VerifiedCoding57.9%% resolvedOfficialApr 2, 2026Details
FrontierMathReasoning26.21%accuracyOfficialApr 2, 2026Details
DeepSWECoding2.65%% resolvedOfficialApr 2, 2026Details
LMArenaChat preference1437source-defined ratingOfficialApr 2, 2026Details
Artificial Analysis Intelligence IndexReasoning50IndexUnverifiedApr 2, 2026Details
Epoch Capabilities IndexReasoning149.1IndexOfficialApr 2, 2026Details
GAIA: A Benchmark for General AI AssistantsAgents37.4%accuracyUnverifiedApr 2, 2026Details
Video-MMEMultimodal84.2%accuracyUnverifiedApr 2, 2026Details
GDPvalAgents1354EloOfficialApr 2, 2026Details
WebDev ArenaChat preference1460EloVerifiedApr 2, 2026Details
Design ArenaChat preference1281EloVerifiedApr 2, 2026Details
CharXivMultimodal81.5%accuracyUnverifiedApr 2, 2026Details
SuperGPQAReasoning71.6%accuracyUnverifiedApr 2, 2026Details
FrontierMath Tier 4Reasoning8.3%accuracyOfficialApr 2, 2026Details
Vibe Code BenchCoding25.57%Overall accuracyVerifiedApr 2, 2026Details
FrontierSWEAgents22%dominance scoreOfficialApr 2, 2026Details