• Joined on 2026-07-22
sora pushed to main at sora/evalstone 2026-08-06 06:48:01 +00:00
922ee3af43 chore: add pyproject.toml and requirements-docker.txt for non-Docker env reproduction
sora pushed to main at sora/evalstone 2026-08-06 02:47:27 +00:00
9fb2a0d2c8 config: increase terminal_bench_v2_1 timeout_multiplier and max_turns
sora pushed to main at sora/evalstone 2026-08-05 05:38:21 +00:00
0d7608c867 feat: add docker image cleanup script for benchmark images
sora pushed to main at sora/evalstone 2026-08-05 03:56:46 +00:00
ba2b5c1772 fix: terminal_bench_v2_1 result collection, apt mirror, and restore run.py env var
sora pushed to main at sora/evalstone 2026-08-04 02:23:50 +00:00
8ad6d26533 feat: add script to pre-download terminal_bench_v2_1 dataset and docker images
sora pushed to main at sora/evalstone 2026-08-03 07:14:07 +00:00
610d6bb2be fix: set LITELLM_LOCAL_MODEL_COST_MAP=True to avoid GitHub fetch timeout
sora pushed to main at sora/evalstone 2026-08-03 07:11:43 +00:00
eb0309baad fix: default API key to EMPTY for local endpoints
sora pushed to main at sora/evalstone 2026-08-03 05:54:20 +00:00
5fdf75e349 chore: remove accidentally committed experimental api_case.sh
sora pushed to main at sora/evalstone 2026-08-03 05:54:01 +00:00
863af5dd12 refactor: move k3_report_test.py to bash/case and make repo-root detection robust
sora pushed to main at sora/evalstone 2026-08-03 05:40:46 +00:00
cdfe59cbee feat: add k3_report_test.py to reproduce available Kimi K3 report benchmarks
sora pushed to main at sora/evalstone 2026-08-03 05:28:52 +00:00
4f33521567 chore: upgrade vendored evalscope to upstream v1.9.1 and reapply local patches
sora pushed to main at sora/evalstone 2026-07-31 06:03:08 +00:00
e388a7561d feat: support --thinking-budget-tokens to control reasoning budget via API
sora pushed to main at sora/evalstone 2026-07-31 03:30:20 +00:00
6ccc38bcb5 docs: restructure README workflow to price first, then select datasets, then test
sora pushed to main at sora/evalstone 2026-07-31 03:04:30 +00:00
bd1e2d7e46 feat: add multi-model pricing, cost prediction and budget filter
sora pushed to main at sora/evalstone 2026-07-31 02:50:25 +00:00
025763be2e feat: refactor GLM52_API_TEST1.sh to generic API runner and add API test README
sora pushed to main at sora/evalstone 2026-07-31 02:44:17 +00:00
11d921071b feat: add benchmark cost calculator and generic API test runner
sora pushed to main at sora/evalstone 2026-07-31 02:36:57 +00:00
b1eb4e116a chore: update evalscope runner, thinking config and webui
sora pushed to main at sora/evalstone 2026-07-29 08:19:05 +00:00
bde21f6624 Replace meaningless trend charts with overall rank and win matrix in results page
sora pushed to main at sora/evalstone 2026-07-29 08:08:08 +00:00
28f22c11e3 Redesign webui: compact layout, search/filter, command preview, progress bar, presets
sora pushed to main at sora/evalstone 2026-07-29 06:37:45 +00:00
8a4c6b279e Remove accidental MARKER_TEST file