Skip to content

[ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

Python · active 2025-10-282026-08-01 (UTC)

Partial coverage11,330 / 12,151 hourly files (93%) · 2 absent upstream · 818 failed, retryable2025-03-222026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
323
Pushes
138
Pull requests
6
Issues
17
Stars
120
Forks
11

Activity over time

Daily event counts in the loaded window

Line chart, 278 days from 2025-10-28 to 2026-08-01. Pushes: 138 total, peak 14 in a day. Pull requests: 6 total, peak 1 in a day. Issues: 17 total, peak 2 in a day. Comments: 21 total, peak 5 in a day. Stars: 120 total, peak 11 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

ContributorContributionsPushesPRsComments
jxhe959410
lockon-n564407
cursor[bot]160011
williamIIliu3001
luccabb2020
KaeHyun2001
bugmaker002010
jitrc1000
Skripkon1000
LLLeoLi1010
Xubqpanda1010
superrrrrr19951000
onestardao1000
gc641533-stack1001
cwyoon-991000
WassupWuK1000
TomLucidor1000
razvangabdumitru-spec1000

Recent activity

Latest issues, pull requests and releases

  • Issue#45cwyoon-992026-05-29 04:28
    poste & woocommerce containers fail again (with "port is already allocated")
  • Pull request#40LLLeoLi2026-05-04 11:54
  • Pull request#38bugmaker002026-04-26 11:50
  • Issue#36WassupWuK2026-03-31 04:37
    The `git-repo` task's evaluation script may be overly strict
  • Issue comment#36lockon-n2026-03-31 04:11
    The `git-repo` task's evaluation script may be overly strict
  • Issue comment#32KaeHyun2026-03-13 05:32
    Gap for DeepSeek v3.2-exp (OpenRouter)
  • Issue#32KaeHyun2026-03-13 05:21
    Gap for DeepSeek v3.2-exp (OpenRouter)
  • Issue comment#29lockon-n2026-02-18 02:16
    Evaluate claude with extended thinking mode
  • Issue#31razvangabdumitru-spec2026-02-12 23:26
    Investigation: dev vs main diverged — commits and potential conflicts
  • Issue#26onestardao2026-02-06 09:00
    Question: using an S-class TXT "tension field" as a high-pressure context for Toolathlon agents?
  • Pull request#22Xubqpanda2025-12-30 11:37
  • Issue#21lockon-n2025-12-27 02:51
    Dedicated Server Fails Due to Hardcoded Port in WebSocket Proxy
  • Issue comment#21lockon-n2025-12-27 02:51
    Dedicated Server Fails Due to Hardcoded Port in WebSocket Proxy
  • Issue#21jitrc2025-12-26 22:57
    Dedicated Server Fails Due to Hardcoded Port in WebSocket Proxy
  • Issue comment#19gc641533-stack2025-12-25 09:20
    Upgrade mcp-remote to support proxy
  • Issue#18lockon-n2025-12-24 10:37
    Public Evaluation Service seems not working now.
  • Issue comment#16lockon-n2025-12-22 08:49
    global deployment
  • Issue#16bugmaker002025-12-22 05:15
    global deployment
  • Issue#15TomLucidor2025-12-18 06:04
    Inclusion of SLMs into the leaderboard
  • Issue#14superrrrrr19952025-12-17 09:04
    Notion MCP Timeout Error
  • Issue#12Skripkon2025-12-09 07:12
    Contradiction in the paper: do frequent tool call errors negatively affect model overall performance?
  • Pull request#13luccabb2025-12-08 21:38
  • Pull request#11luccabb2025-12-05 05:07
  • Issue comment#4lockon-n2025-11-30 04:01
    运行测试脚本的时候出现python的问题
  • Issue#8lockon-n2025-11-30 03:56
    task label

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 120 stars here means stars gained during the window, not the repo's star count.