sgl-project/sglang

Extensive benchmarking of reasoning models including variance

Open

#3,725 opened on Feb 20, 2025

View on GitHub
 (3 comments) (0 reactions) (1 assignee)Python (6,216 forks)auto 404
good first issue

Repository metrics

Stars
 (28,442 stars)
PR merge metrics
 (Avg merge 2d 1h) (1,000 merged PRs in 30d)

Description

In their R1 repo deepseek people recommend to estimate PASS@1 by asking the same question various times. We implemented that into our Reasoning benchmark. Additionaly to the averaged accuracy we report also average standard error as a measurement of uncertainty. Ideally that would include some plots.

Now we want to perform experiments how the results change under

  • repeated experiment with same hyperparameters
  • increased number of trials

I think the AIME 2024 is suited to this experiment because LIMO is quiet large and it will take long time to run experiments with a large number of trials.

Please see recently merged brach that includes measurement of uncertainty in reasoning models answers for more details and detailed explanation of the metrics.

Feel free to reach out to me if you have further questions.

Contributor guide

Research direction
Review the recently merged PR (#3677) and the existing reasoning benchmark code to understand how to add variance metrics and plotting for multiple trials.
Tech stack
python
Domain
machine learningbackend
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
GitPythonBasic statistics
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30