Releases: AISBench/benchmark
Releases · AISBench/benchmark
v3.1-20260415-master
🌟 Release Note
📦 Docker Images For This Release
| name | arch | python version | offline resources | image size | tar.gz size |
|---|---|---|---|---|---|
| v3.1-20260415-master_aarch64_py_310 | aarch64 | 3.10 | https://aisbench.obs.cn-north-4.myhuaweicloud.com/images/benchmark/github/ais_bench_benchmark_image_v3.1-20260415-master_aarch64_py_310.tar.gz | 2.77 GB | 846 MB |
| v3.1-20260415-master_x86_64_py_415 | x86_64 | 3.10 | https://aisbench.obs.cn-north-4.myhuaweicloud.com/images/benchmark/github/ais_bench_benchmark_image_v3.1-20260415-master_x86_64_py_310.tar.gz | 3.04 GB | 926 MB |
👉 Click Here For Docker Images Usage Guidance
📄 Document For This Release
https://ais-bench-benchmark-rf.readthedocs.io/zh-cn/v3.1-20260415-master/
What's Changed
- [bugfix] Let trust_remote_code take effect by @SJTUyh in #226
- Update textvqa.py by @1037husterljx in #230
- 【Feature】 Adapt util/worker config typing and defaults for custom cfg by @GaoHuaZhang in #239
- 【Feature】add SWE-bench eval task, dataset loader, and summarizer integration by @GaoHuaZhang in #240
- 【Feature】Support SWE-Bench benchmark pipeline and Mini SWE Agent integration by @GaoHuaZhang in #241
- 【Feature】add SWE-bench example configs and bilingual user guide by @GaoHuaZhang in #191
- [Bugfix] support vita model by @Huangzjun in #237
- [feature][for merge][part0]tau2 bench code by @SJTUyh in #249
- [feature][for merge][part1]tau2 bench docs by @SJTUyh in #250
- [feature][for merge][part2] tau2 bench test cases by @SJTUyh in #251
- [docs] 20260415 pre-release docs update by @SJTUyh in #252
New Contributors
- @1037husterljx made their first contribution in #230
- @Huangzjun made their first contribution in #237
Full Changelog: v3.1-20260330-master...v3.1-20260415-master
😄 Thanks for using AISBench/benchmark !
v3.1-20260330-master
🌟 Release Note
📦 Docker Images For This Release
| name | arch | python version | offline resources | tar.gz size | image size |
|---|---|---|---|---|---|
| v3.1-20260330-master_aarch64_py_310 | aarch64 | 3.10 | https://aisbench.obs.cn-north-4.myhuaweicloud.com/images/benchmark/github/ais_bench_benchmark_image_v3.1-20260330-master_aarch64_py_310.tar.gz | 2.77 GB | 850 MB |
| v3.1-20260330-master_x86_64_py_310 | x86_64 | 3.10 | https://aisbench.obs.cn-north-4.myhuaweicloud.com/images/benchmark/github/ais_bench_benchmark_image_v3.1-20260330-master_x86_64_py_310.tar.gz | 3.04 GB | 950 MB |
👉 Click Here For Docker Images Usage Guidance
📄 Document For This Release
https://ais-bench-benchmark-rf.readthedocs.io/zh-cn/v3.1-20260330-master/
😄 Thanks for using AISBench/benchmark !
v3.0-20251219-master (pre-release)
🌟 Release Note
📦 Docker Images For This Release
👉 Click Here For Docker Images Usage Guidance
📄 Document For This Release
https://ais-bench-benchmark-rf.readthedocs.io/zh-cn/v3.0-20251219-master/