supermarket

Language

Qwen2.5-7B-Instruct

By Alibaba Group, in the Qwen family.

Released
19 Sep 2024
Status
Legacy
Context
131.1K
Max output
—
Input per 1M tokens
—
Output per 1M tokens
—
Open weights
Yes
License
apache-2.0
Parameters
7B
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 & reasoning3.81052 of 4
Agentic tool use7.8Not ranked1 of 2

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 solved0.0%Independent—30 Aug 2026Epoch AI
DTBench (Decision Theory Benchmark)Accuracy (capability questions)47.7%Third party——https://conceptualreasoning.ai/dtbench via Epoch AI
LMCA (Language Model Conceptual Argumentation)Correlation with expert ratings (Pearson r)0.0642Third party——https://conceptualreasoning.ai/lmca via Epoch AI
MMLUAccuracy72.9%Third party——Stanford CRFM Leaderboard via Epoch AI

Scientific reasoning

Scientific reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GPQA DiamondAccuracy35.5%Independent—30 Aug 2026Epoch AI

Mathematics

Mathematics results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
OTIS Mock AIME 2024-2025Accuracy2.5%Independent—30 Aug 2026Epoch AI

Agentic tool use

Agentic tool use results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
BALROGAverage progress7.8%Third party——https://balrogai.com/ via Epoch AI

Other Qwen versions

Sources