Qwen 2.5

release date unknown

BenchAtlas Index

as of 2026-07-14

Not enough benchmark coverage for a composite score (needs ≥4 families across ≥3 categories). The per-benchmark evidence below stands on its own — sparse coverage is an evidence gap, not a low score.

Benchmark evidence

0 results

No bare-model results yet.

Agent + model results

systems, not bare-model scores

agent + model SWE-agent + Qwen 2.5	SWE-bench Verified	40.2 %	community	SWE-bench Leaderboard
agent + model SWE-Fixer + Qwen 2.5	SWE-bench Verified	32.8 %	community	SWE-bench Leaderboard
agent + model SWE-Fixer + Qwen 2.5	SWE-bench Verified	30.2 %	unverified	SWE-bench Leaderboard
agent + model SWE-Fixer + Qwen 2.5	SWE-bench Lite	24.7 %	community	SWE-bench Leaderboard
agent + model SWE-Fixer + Qwen 2.5	SWE-bench Lite	23.3 %	unverified	SWE-bench Leaderboard

These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.

Related variants

Qwen 7B Qwen 14B