maka/docs/eval at main - maka - Gitea: Git with a cup of tea

mirrors/maka

0 Fork 0

mirror of https://github.com/apache/maka.git synced 2026-10-28 17:04:39 +08:00

Files

T

History

AstroHan 173aed934f docs(eval): report the three-arm edit-contract comparison (#3158 )

Report + per-task CSV for the three-arm file-editing tool contract experiment on Terminal-Bench 2.1 with deepseek-v4-flash: str_replace_editor vs @deepseek-ai/dsh-tool-fs vs a repo-authored apply_patch plugin. No detectable difference (56/56/53 of 86 scored tasks); the report states this as a failure to detect, not equivalence. Docs only.

Generated-by: Claude Code

2026-09-21 11:29:06 +08:00

terminal-bench-2.1-deepseek-v4-flash-edit-contracts.csv

docs(eval): report the three-arm edit-contract comparison (#3158 )

2026-09-21 11:29:06 +08:00

terminal-bench-2.1-deepseek-v4-flash-edit-contracts.md

docs(eval): report the three-arm edit-contract comparison (#3158 )

2026-09-21 11:29:06 +08:00

terminal-bench-2.1-deepseek-v4-flash-four-arm.csv

docs(eval): record the four-arm Terminal-Bench 2.1 comparison (#2208 )

2026-08-05 16:52:43 +08:00

terminal-bench-2.1-deepseek-v4-flash-four-arm.md

chore: add ASF source headers and a release header audit gate (#3397 )