sora 1308ddd251 feat(run.py): add --thinking-max-tokens-scale and official suite ...

- Add --thinking-max-tokens-scale to multiply max_tokens when
  --thinking is enabled.
- Add 'official' suite covering all benchmarks in the public
  comparison tables (Kimi/GLM/DS etc).
- Print scale factor in run summary when thinking is on.

2026-07-23 02:57:53 +00:00

bash

feat(run.py): add --thinking-max-tokens-scale and official suite

2026-07-23 02:57:53 +00:00

config

docs: add resource prep section and sync docker/bash helpers

2026-07-23 02:18:15 +00:00

evalscope

all

2026-07-21 09:32:49 +00:00

scripts

all

2026-07-22 03:26:58 +00:00

.dockerignore

all

2026-07-21 09:32:49 +00:00

.gitignore

docs: add resource prep section and sync docker/bash helpers

2026-07-23 02:18:15 +00:00

DOCKER_BUILD.md

all

2026-07-21 09:32:49 +00:00

DOCKER_README.md

all

2026-07-21 09:32:49 +00:00

Dockerfile.withcode

all

2026-07-21 09:32:49 +00:00

EVALUATION_GUIDE.md

all

2026-07-21 09:32:49 +00:00

HOWTO_EVAL_NEW_MODEL.md

all

2026-07-21 09:32:49 +00:00

myread.md

feat(pull_swe_bench_images): support comma-separated --dataset

2026-07-23 02:34:49 +00:00

P800模型能力评测结果 - DS4-Flash-INT8-NO-Thinking-2.0-FULL.csv

all

2026-07-22 03:26:58 +00:00

Description

No description provided

67 MiB

Languages

Python 83.2%

TypeScript 11%

HTML 3.2%

JavaScript 1.1%

CSS 0.6%

Other 0.8%