supermarket

Language

Qwen3-235B-A22B-Instruct-2507

By Alibaba Group, in the Qwen family.

Released
21 Jul 2025
Status
Legacy
Context
262.1K
Max output
32.8K
Input per 1M tokens
$0.23
Output per 1M tokens
$0.92
Open weights
Yes
License
apache-2.0
Parameters
235B, 22B active
Knowledge cutoff
—
Reasoning
No
Modalities
text → text

Category scores

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

Category scores
CategoryScoreRankCoverage
Knowledge & reasoning27.7Not ranked1 of 4
Coding & software engineering59.6Not ranked1 of 5
Human preference53.2Not ranked1 of 5

Benchmark results

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

Knowledge & reasoning

Knowledge & reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
DTBench (Decision Theory Benchmark)Accuracy (capability questions)78.4%Third party——https://conceptualreasoning.ai/dtbench via Epoch AI
LMCA (Language Model Conceptual Argumentation)Correlation with expert ratings (Pearson r)0.2352Third party——https://conceptualreasoning.ai/lmca via Epoch AI
MMLU-ProAccuracy83.0%Self-reported——EvalEval via Hugging Face Community Evals

Coding & software engineering

Coding & software engineering results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Aider PolyglotPercent correct59.6%Third party——https://aider.chat/docs/leaderboards/ via Epoch AI
WeirdML (v2)Average accuracy38.7%Third party——WeirdML Leaderboard via Epoch AI

Human preference

Human preference results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Text Arena (arena.ai)Arena score (Elo scale)1422Independent—25 Sep 2026Arena
Text Arena (arena.ai)Votes97815Independent—25 Sep 2026Arena

Other Qwen versions

Sources

Qwen3-235B-A22B-Instruct-2507: benchmarks, price and specs · supermarket.dev