Skip to content
Navigation Menu
Sign in
Appearance settings
Platform
AI CODE CREATION
GitHub Copilot
Write better code with AI
GitHub Copilot app
Direct agents from issue to merge
MCP Registry
Integrate external tools
DEVELOPER WORKFLOWS
Actions
Automate any workflow
Codespaces
Instant dev environments
Issues
Plan and track work
Code Review
Manage code changes
Code Quality
Enforce quality at merge
APPLICATION SECURITY
GitHub Advanced Security
Find and fix vulnerabilities
Code security
Secure your code as you build
Secret protection
Stop leaks before they start
EXPLORE
Why GitHub
Documentation
Blog
Changelog
Marketplace
View all features
Solutions
BY COMPANY SIZE
Enterprises
Small and medium teams
Startups
Nonprofits
BY USE CASE
App Modernization
DevSecOps
DevOps
CI/CD
View all use cases
BY INDUSTRY
Healthcare
Financial services
Manufacturing
Government
View all industries
View all solutions
Resources
EXPLORE BY TOPIC
AI
Software Development
DevOps
Security
View all topics
EXPLORE BY TYPE
Customer stories
Events & webinars
Ebooks & reports
Business insights
GitHub Skills
SUPPORT & SERVICES
Documentation
Customer support
Community forum
Trust center
Partners
View all resources
Open Source
COMMUNITY
GitHub Sponsors
Fund open source developers
PROGRAMS
Security Lab
Maintainer Community
GitHub Stars
Archive Program
REPOSITORIES
Topics
Trending
Collections
Enterprise
ENTERPRISE SOLUTIONS
Enterprise platform
AI-powered developer platform
AVAILABLE ADD-ONS
GitHub Advanced Security
Enterprise-grade security features
Copilot for Business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Pricing
Search
/
Sign in
Sign up
Appearance settings
You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
Dismiss alert
{{ message }}
EleutherAI
lm-evaluation-harness
Repository navigation
Code
Issues
635
(635)
Pull requests
523
(523)
Discussions
Actions
Projects
Security and quality
Insights
More
items
All pull requests
Labels
11
(11)
Milestones
1
(1)
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
523
(523)
Closed
2,037
(2,037)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
Omit SAE decoder bias for additive CSV steering
#4366
·
sdivyanshu90
opened
Oct 12, 2026
Contributor
·
·
1
1
Preserve model temperature when sampling is explicitly enabled
#4365
·
sdivyanshu90
opened
Oct 12, 2026
Contributor
·
·
1
1
feat(tasks): add AboveBoard 52 sovereign Canadian marine benchmark
#4362
·
Rolosolo
opened
Oct 11, 2026
·
·
1
fix(aclue): restore dataset loading without remote scripts
#4360
·
ChaceQs
opened
Oct 11, 2026
·
·
1
fix(afrobench): rename nollysenti columns after the dataset dropped its loading script
#4359
·
chrikrah
opened
Oct 11, 2026
·
·
1
Preserve nested generation options when batching requests
#4358
·
AaravMehta-07
opened
Oct 10, 2026
·
·
1
Add PT-BR typed decisions (Brazilian Portuguese closed-question tasks)
#4357
·
antonio-mello-ai
opened
Oct 10, 2026
·
·
1
Preserve leaf names for group reference overrides
#4356
·
sdivyanshu90
opened
Oct 10, 2026
Contributor
·
·
1
1
Fix direct-task bypass metric results
#4355
·
sdivyanshu90
opened
Oct 10, 2026
Contributor
·
·
1
1
fix(models): preserve None values in undistribute
#4352
·
joshduplaa
opened
Oct 10, 2026
·
·
1
1
fix(mgsm): match the native exemplars' answer format in native_cot strict-match
#4351
·
usmanmateen
opened
Oct 10, 2026
·
·
1
1
fix(arabic_leaderboard): include Arabic MMLU in the leaderboard groups
#4349
·
samycc777
opened
Oct 9, 2026
·
·
fix(arabic_leaderboard): list the answer choices in the SciQ prompt
#4348
·
samycc777
opened
Oct 9, 2026
·
·
1
Add LLMSQL 2.0 Text-to-SQL task
#4347
·
DzmitryPihulski
opened
Oct 9, 2026
·
·
1
fix(llama3): keep question whitespace in mmlu_cot_llama prompt
#4346
·
mertkayacs
opened
Oct 9, 2026
·
·
1
Add Saraiki LLM Benchmark (saraiki_bench)
#4344
·
themohal
opened
Oct 9, 2026
·
·
1
fix(utils): default temperature to 0.0 when do_sample is unset (vLLM sampled greedy tasks)
#4343
·
avifenesh
opened
Oct 8, 2026
·
·
1
Make direct Python task names deterministic
#4341
·
sdivyanshu90
opened
Oct 8, 2026
Contributor
·
·
1
1
Fix empty sample selection in task document iterator
#4340
·
sdivyanshu90
opened
Oct 8, 2026
Contributor
·
·
1
1
fix(turkishmmlu): take the last standalone letter in the CoT get-choice filter
#4339
·
Anri-Lombard
opened
Oct 8, 2026
Contributor
·
·
fix(mmlu-redux): only take a standalone answer letter in the generative filter
#4338
·
Anri-Lombard
opened
Oct 8, 2026
Contributor
·
·
fix(arab_culture_completion): return the gold index so it matches the choices
#4337
·
Anri-Lombard
opened
Oct 8, 2026
Contributor
·
·
fix(score): make options_consistency_rate swap labels instead of collapsing them
#4336
·
Anri-Lombard
opened
Oct 8, 2026
Contributor
·
·
Warn when a group's declared aggregate metric matches no task results
#4333
·
jurayh
opened
Oct 7, 2026
·
·
1
fix(janitor): make the C++ janitor match Python semantics on non-ASCII text
#4332
·
zstring
opened
Oct 7, 2026
·
4 of 5 tasks
·
·
1
1
Previous
1
2
3
4
5
6
7
…
21
Next
You can’t perform that action at this time.
×
×
Рекламное место
свободно