fork from [NeurIPS 2025] MergeBench: A Benchmark for Merging Domain-Specialized LLMs
active 2025-05-22 → 2026-06-11 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 386 days from 2025-05-22 to 2026-06-11. Pushes: 2 total, peak 1 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 7 total, peak 2 in a day. Comments: 5 total, peak 1 in a day. Stars: 23 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 |
|---|---|---|---|---|
| yifei-he | 7 | 2 | 0 | 3 |
| babangain | 3 | 0 | 0 | 0 |
| KaiyangLi1992 | 2 | 0 | 0 | 1 |
| Zheng-Jay | 2 | 0 | 0 | 1 |
| nthehai01 | 1 | 0 | 1 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#17yifei-he2026-06-11 22:58Request: fine-tuned expert performance on individual tasks
- Issue comment#14yifei-he2026-04-04 02:29Performance of finetuned models on different tasks
- Issue#13Zheng-Jay2026-02-26 03:36Request for Evaluation Scripts: Generalization and Forgetting Analysis
- Issue comment#10KaiyangLi19922026-01-28 21:21How to Run Math CoT 0-shot Evaluation? Not Found in evaluate.sh
- Issue#10KaiyangLi19922026-01-28 00:37How to Run Math CoT 0-shot Evaluation? Not Found in evaluate.sh
- Pull request#8nthehai012025-12-09 18:42
- Issue comment#5yifei-he2025-09-29 19:22Request for per-task performance results
- Issue#4yifei-he2025-09-18 18:37Seeking Clarification Regarding Normalized performance
- Issue comment#2yifei-he2025-09-18 18:34Llama-3.1-8B-Instruct_math shows poor performance on GSM8K-CoT
- Issue comment#2Zheng-Jay2025-09-14 12:47Llama-3.1-8B-Instruct_math shows poor performance on GSM8K-CoT
- Issue#4babangain2025-07-08 15:04Seeking Clarification Regarding Normalized performance
- Issue#3babangain2025-07-08 12:31Evaluation scripts on Mergebench dataset
- Issue#3babangain2025-07-05 13:42Evaluation scripts on Mergebench dataset
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 23 stars here means stars gained during the window, not the repo's star count.