Skip to content

Add OpenEvo v0.1.10 leaderboard results - #2

Open
Estevan-Uni wants to merge 1 commit into
InternScience:mainfrom
Estevan-Uni:add-openevo-v0.1.10
Open

Add OpenEvo v0.1.10 leaderboard results#2
Estevan-Uni wants to merge 1 commit into
InternScience:mainfrom
Estevan-Uni:add-openevo-v0.1.10

Conversation

@Estevan-Uni

Copy link
Copy Markdown

OpenEvo v0.1.10 ResearchClawBench results

This PR adds the verified leaderboard-only result for OpenEvo v0.1.10.

  • Model: GPT-5.5
  • Official task coverage: 40/40
  • Mean selected score: 32.68725
  • Runtime-estimated leaderboard cost: USD 92.908827
  • API-equivalent token estimate: USD 89.381920
  • Selection policy: best accepted result per task
  • Details: details_exported=false; full reports, code, outputs, images, and token audit are retained in the accompanying result package

The three modified files were generated from the official Home leaderboard-only importer and
validated against its schema. No new benchmark task is being submitted.

@black-yt

Copy link
Copy Markdown
Collaborator

Hello, thank you for your interest in our work. If you wish to upload the results, please send the runs package to xu_wanghan@sjtu.edu.cn. Please remove the data folder from the runs package to avoid excessive file size.
Snipaste_2026-08-06_17-54-19

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants