UnifyBench

RankingSWE-bench Pro

SWE-bench Pro

Data updated 22 Oct 2026

Bucket
Coding
Unit
percent
Direction
Higher is better
Version
public
Display harness
SWE-bench Pro reported
Board
https://labs.scale.com/leaderboard/swe_bench_pro

Compare published benchmark results with category weights →

Models

Results are ordered by score in the display harness, followed by models with no result. Other harnesses are listed separately below. Missing results remain unknown.

26–50 of 471 entries

ModelScoreEvidenceSource-recorded date
c4ai-command-r7b-arabic-02-2025Cohere———
chatglm-6bZ.ai———
chatglm2-6bZ.ai———
chatglm2-6b-32kZ.ai———
chatglm3-6bZ.ai———
chatglm3-6b-128kZ.ai———
chatglm3-6b-32kZ.ai———
Claude Fable 5Anthropic———
Claude Fable 5.1Anthropic———
Claude Haiku 4.5Anthropic———
Claude Haiku 5.5Anthropic———
Claude Opus 4.5Anthropic———
Claude Opus 4.7Anthropic———
Claude Opus 4.8Anthropic———
Claude Opus 5.5Anthropic———
Claude Sonnet 4.5Anthropic———
Claude Sonnet 4.6Anthropic———
Claude Sonnet 5Anthropic———
Claude Sonnet 5.5Anthropic———
codegeex2-6bZ.ai———
codegeex4-all-9bZ.ai———
CodeGemma 7B ITGoogle———
Codestral 2508Mistral———
cogagent-9b-20241220Z.ai———
cogagent-chat-hfZ.ai———

Other harnesses

These runs use other harnesses. Capability scoring matches configurations separately; model details identify which source records contribute.

ModelScoreHarnessEvidenceSource-recorded date
Claude Fable 5Anthropic80%Anthropic SWE-bench Pro reported systemlab self-report

Systemcard section8.2: SWEPro average overfive trials, adaptive max effort/defaultsampling. Agent equivalence to miniSWE is not documented; retain distinct reported-system harness, exclude preferred-agent aggregate.

2026-09-01
Claude Fable 5.1Anthropic81.2%Anthropic SWE-bench Pro reported systemlab self-report

Systemcard section8.2: SWEPro average overfive trials, adaptive max effort/defaultsampling. Agent equivalence to miniSWE is not documented; retain distinct reported-system harness, exclude preferred-agent aggregate.

2026-09-01