Skip to content

A new tool learning benchmark aiming at well-balanced stability and reality, based on ToolBench.

active 2024-05-272026-05-20 (UTC)

Partial coverage20,530 / 26,286 hourly files (78%) · 2 absent upstream · 5,753 failed, retryable2023-08-152026-08-14 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
125
Pushes
12
Pull requests
2
Issues
15
Stars
81
Forks
8

Activity over time

Daily event counts in the loaded window

Line chart, 724 days from 2024-05-27 to 2026-05-20. Pushes: 12 total, peak 3 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 15 total, peak 1 in a day. Comments: 7 total, peak 1 in a day. Stars: 81 total, peak 2 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Issue comment#36Shivansh-12342026-02-02 11:47
    Still need OpenAI API key after FAC eval model?
  • Issue#36Shivansh-12342026-01-30 23:17
    Still need OpenAI API key after FAC eval model?
  • Issue comment#34yoshua1332025-12-12 00:13
    toolenv2404_filtered工具是否不完整?TOOLBENCH_KEY 申请能否通过一下
  • Issue#35vmanvs2025-12-06 16:30
    Problem with vllm version
  • Issue#34Yaoyoay2025-12-05 10:52
    toolenv2404_filtered工具是否不完整?TOOLBENCH_KEY 申请能否通过一下
  • Issue#3211430377832025-10-22 08:14
    服务器上的rapidAPI key是否已经失效?
  • Issue#29James4Ever02025-09-21 02:31
    Vimgolf, Cybergod and CTF environments integration, WebUI computer operation recorder integration
  • Issue#30jhsansom2025-09-19 17:49
    Do you provide the evaluation results?
  • Issue#28floatingbigcat2025-04-18 06:32
    Why further tool bench key is needed?
  • Issue#25Octobrist2024-11-22 02:07
    Is the server still working properly?
  • Issue#23Dlxxx2024-10-25 06:30
    Looking for a ToolBench key
  • Issue#15farawayxxx2024-10-18 02:41
    inference problem
  • Issue comment#21WeiminXiong2024-09-29 06:24
    ToolBench Key
  • Issue comment#21zhaoqianyue2024-09-27 12:33
    ToolBench Key
  • Issue#22Hanlin10042024-09-27 07:36
    ToolBench Key
  • Pull request#20kingb122024-09-04 04:42
  • Issue comment#18kingb122024-08-18 04:34
    Did ToolBench server crashed?
  • Pull request#20kingb122024-08-18 04:22
  • Issue#18Reason-Wang2024-08-01 05:23
    Did ToolBench server crashed?
  • Issue comment#5importpandas2024-07-28 11:39
    Could you release the reproduction data for your result
  • Issue comment#16farawayxxx2024-06-29 08:52
    role error
  • Issue#13stanpcf2024-06-21 04:12
    applied for toolbench_key but no one responded
  • Issue#12YenFuLin2024-06-05 04:56
    How is native LLM on this benchmark?
  • Issue#11JuhaoLiang19972024-05-28 03:56
    Implementation of DFSDT and ReACT

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 81 stars here means stars gained during the window, not the repo's star count.