Complex Function Calling Benchmark.
active 2025-08-02 → 2026-04-17 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 259 days from 2025-08-02 to 2026-04-17. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 9 total, peak 3 in a day. Comments: 6 total, peak 2 in a day. Stars: 27 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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| Cyprianhenry | 6 | 0 | 0 | 1 |
| lucenzhong | 4 | 0 | 0 | 4 |
| vantaa89 | 1 | 0 | 0 | 0 |
| Aliasgarsaifee | 1 | 0 | 0 | 0 |
| antonpibm | 1 | 0 | 0 | 1 |
| Huluwa-kong | 1 | 0 | 0 | 0 |
| zhujiaying-mcpmark-1 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#12Cyprianhenry2026-02-18 02:16A bug in the `PostToolUse` hook causes excessive duplication of observations in the database, with each tool use creating 6-10 identical records instead of one. Despite efforts to clean up 51,140 duplicate entries and leave only 6,098 unique observations, the issue reoccurs immediately after new tool usage. Investigation confirms there is only one registered PostToolUse hook, and no additional configuration anomalies, indicating the problem likely lies in the `worker-service.cjs` file, which lac
- Issue#12Cyprianhenry2026-02-18 02:16A bug in the `PostToolUse` hook causes excessive duplication of observations in the database, with each tool use creating 6-10 identical records instead of one. Despite efforts to clean up 51,140 duplicate entries and leave only 6,098 unique observations, the issue reoccurs immediately after new tool usage. Investigation confirms there is only one registered PostToolUse hook, and no additional configuration anomalies, indicating the problem likely lies in the `worker-service.cjs` file, which lac
- Issue comment#12Cyprianhenry2026-02-18 02:15A bug in the `PostToolUse` hook causes excessive duplication of observations in the database, with each tool use creating 6-10 identical records instead of one. Despite efforts to clean up 51,140 duplicate entries and leave only 6,098 unique observations, the issue reoccurs immediately after new tool usage. Investigation confirms there is only one registered PostToolUse hook, and no additional configuration anomalies, indicating the problem likely lies in the `worker-service.cjs` file, which lac
- Issue#12Cyprianhenry2026-02-18 02:13A bug in the `PostToolUse` hook causes excessive duplication of observations in the database, with each tool use creating 6-10 identical records instead of one. Despite efforts to clean up 51,140 duplicate entries and leave only 6,098 unique observations, the issue reoccurs immediately after new tool usage. Investigation confirms there is only one registered PostToolUse hook, and no additional configuration anomalies, indicating the problem likely lies in the `worker-service.cjs` file, which lac
- Issue#11Cyprianhenry2025-12-28 03:11## Code Review: bugfix/linger
- Issue#10Cyprianhenry2025-12-23 01:02http://xx.xx.xx.xx:8000/v1
- Issue#9zhujiaying-mcpmark-12025-11-13 06:36关于数据集的时效性问题
- Issue comment#8lucenzhong2025-11-04 07:55Please add a license to this repo
- Issue#7Aliasgarsaifee2025-09-19 13:35Getting stuck at tool call in evaluation of Qwen3
- Issue comment#6antonpibm2025-09-14 09:47Ground truth response in the evaluation dataset
- Issue comment#6lucenzhong2025-09-11 07:43Ground truth response in the evaluation dataset
- Issue comment#4lucenzhong2025-08-20 02:08GPTRunner discards text response when there is tool call
- Issue comment#5lucenzhong2025-08-20 02:04GPT-5 performs very bad on this benchmark
- Issue#5Huluwa-kong2025-08-15 01:34GPT-5 performs very bad on this benchmark
- Issue#4vantaa892025-08-14 11:50GPTRunner discards text response when there is tool call
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 27 stars here means stars gained during the window, not the repo's star count.