supermarket

Language

Qwen3.6-35B-A3B

By Alibaba Group, in the Qwen family.

Released
16 Apr 2026
Status
Legacy
Context
262.1K
Max output
65.5K
Input per 1M tokens
$0.38
Output per 1M tokens
$2.25
Open weights
Yes
License
apache-2.0
Parameters
35B, 3B active
Knowledge cutoff
—
Reasoning
Yes
Modalities
text, image, video → text

Category scores

Out of 100, from independent and third-party results only, by method category-2026-09-29.1.

Category scores
CategoryScoreRankCoverage
Knowledge & reasoning28.5612 of 4

Benchmark results

Every result we hold for this model, with who ran it and where it was published.

Knowledge & reasoning

Knowledge & reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Chess PuzzlesPuzzles solved26.0%Independent—7 Aug 2026Epoch AI
Chess PuzzlesPuzzles solved4.0%Independentnone7 Aug 2026Epoch AI
DTBench (Decision Theory Benchmark)Accuracy (capability questions)73.9%Third party——https://conceptualreasoning.ai/dtbench via Epoch AI
Humanity's Last Exam (HLE)Accuracy21.4%Self-reported——Model Card via Hugging Face Community Evals
LMCA (Language Model Conceptual Argumentation)Correlation with expert ratings (Pearson r)0.297Third party——https://conceptualreasoning.ai/lmca via Epoch AI
MMLU-ProAccuracy85.2%Self-reported——Model Card via Hugging Face Community Evals
Mystery Game PuzzlesPuzzles solved22.0%Independentnone27 Aug 2026Epoch AI

Scientific reasoning

Scientific reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GPQA DiamondAccuracy84.8%Independentnone7 Aug 2026Epoch AI
GPQA DiamondAccuracy83.8%Independent—7 Aug 2026Epoch AI
GPQA DiamondAccuracy86.0%Self-reported——Model Card via Hugging Face Community Evals
Surface Evolver BenchMean score (partial credit)44.4%Third party——https://yhenon.github.io/surface-evolver-llm-eval/ via Epoch AI

Mathematics

Mathematics results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
FrontierMath Tiers 1-3Accuracy20.4%Independentnone30 Aug 2026Epoch AI
FrontierMath Tiers 1-3Accuracy17.5%Independent—29 Aug 2026Epoch AI
OTIS Mock AIME 2024-2025Accuracy86.7%Independent—7 Aug 2026Epoch AI
OTIS Mock AIME 2024-2025Accuracy68.9%Independentnone7 Aug 2026Epoch AI

Coding & software engineering

Coding & software engineering results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Terminal-Bench 2.0Accuracy (mean over trials)23.0%Third party——https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI
WeirdML (v2)Average accuracy34.5%Third party——https://htihle.github.io/weirdml.html via Epoch AI

Other Qwen versions

Sources