supermarket

Language

Qwen3-8B

By Alibaba Group, in the Qwen family.

Released
29 Apr 2025
Status
Legacy
Context
131.1K
Max output
8.2K
Input per 1M tokens
$0.18
Output per 1M tokens
$0.70
Open weights
Yes
License
apache-2.0
Parameters
8B
Knowledge cutoff
—
Reasoning
Yes
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 & reasoning5.21032 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 solved5.0%Independent—27 Aug 2026Epoch AI
Chess PuzzlesPuzzles solved0.0%Independentnone27 Aug 2026Epoch AI
DTBench (Decision Theory Benchmark)Accuracy (capability questions)59.7%Third party——https://conceptualreasoning.ai/dtbench via Epoch AI
LMCA (Language Model Conceptual Argumentation)Correlation with expert ratings (Pearson r)0.0882Third party——https://conceptualreasoning.ai/lmca via Epoch AI

Scientific reasoning

Scientific reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GPQA DiamondAccuracy56.8%Independent—27 Aug 2026Epoch AI
GPQA DiamondAccuracy47.5%Independentnone27 Aug 2026Epoch AI

Mathematics

Mathematics results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
OTIS Mock AIME 2024-2025Accuracy56.1%Independent—27 Aug 2026Epoch AI
OTIS Mock AIME 2024-2025Accuracy22.2%Independentnone27 Aug 2026Epoch AI

Long context

Long context results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Fiction.LiveBench% correct at 16K tokens (Epoch's column)62.1%Third party——Fiction.live leaderboard via Epoch AI

Other Qwen versions

Sources