1.xinxuxin / keystone-bench
A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.
+600 stars
from 473 · score 6.40
Trending repositories
Ranked by Attention Score: stars gained over the last 30 complete days
9 repositories by Attention Score · Oct 4, 2026 – Nov 2, 2026 (UTC)
2.facebookresearch / swe-sweep
How many bugs can LMs find & fix in large codebases?
+175 stars
from 40 · score 5.17
3.zalandoresearch / fashion-mnist
A MNIST-like fashion product database. Benchmark :point_down:
+43 stars
from 12,836 · score 3.78
4.sunlabuiuc / PyHealth
A deep learning toolkit for healthcare AI: EHR (MIMIC, eICU, OMOP), clinical text, signals and imaging. 30+ models, reproducible pipelines.
+31 stars
from 1,661 · score 3.47
5.MichaelGrupp / evo
Python package for the evaluation of odometry and SLAM
+29 stars
from 4,324 · score 3.40
6.python / pyperformance
Python Performance Benchmark Suite
+13 stars
from 1,032 · score 2.64
7.molecularsets / moses
Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models
+7 stars
from 990 · score 2.08
8.tarasko / picows
Ultra-fast websocket client and server for asyncio
+3 stars
from 291 · score 1.39
9.flow-project / flow
Computational framework for reinforcement learning in traffic control
+2 stars
from 1,189 · score 1.10