UnifyBench

RankingOSWorld-Verified

OSWorld-Verified

Data updated 22 Oct 2026

Bucket
Agentic
Unit
percent
Direction
Higher is better
Version
verified
Display harness
OSWorld-Verified reported
Board
https://os-world.github.io/

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
chatglm-6bZ.ai———
chatglm2-6bZ.ai———
chatglm2-6b-32kZ.ai———
chatglm3-6bZ.ai———
chatglm3-6b-128kZ.ai———
chatglm3-6b-32kZ.ai———
Claude Fable 5.1Anthropic———
Claude Haiku 4.5Anthropic———
Claude Haiku 5.5Anthropic———
Claude Opus 4.5Anthropic———
Claude Opus 4.6Anthropic———
Claude Opus 4.7Anthropic———
Claude Opus 4.8Anthropic———
Claude Opus 5.5Anthropic———
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———
cogagent-vqa-hfZ.ai———
cogvlm-chat-hfZ.ai———
cogvlm2-llama3-chat-19BZ.ai———