1.Folkbench / folkbench
TranslatedOpen-source AI API relay benchmark, rankings & switcher for Claude Code / Codex: measured availability, latency and price
+456 stars
from 3,866 · score 6.12
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
11 repositories by Attention Score · Oct 29, 2026 – Nov 4, 2026 (UTC)
2.langfuse / langfuse
🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
- analytics
- llm
- llmops
- large-language-models
- openai
- self-hosted
- +13 more
+355 stars
from 36,659 · score 5.87
3.facebookresearch / InteractiveWorld
This is the official repo for paper InteractiveWorld A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants
+184 stars
from 30 · score 5.22
4.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.
+139 stars
from 994 · score 4.94
5.Prophetlab / Investor-Last-Exam
Investor’s Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?
+138 stars
from 2 · score 4.93
6.Arize-ai / phoenix
AI Observability & Evaluation
- llmops
- ai-monitoring
- ai-observability
- llm-eval
- aiengineering
- datasets
- +10 more
+95 stars
from 12,048 · score 4.56
7.openai / evals
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
+37 stars
from 19,670 · score 3.64
8.ConardLi / easy-dataset
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval
- dataset
- javascript
- llm
- fine-tuning
- rag
+33 stars
from 15,049 · score 3.53
9.facebookresearch / swe-sweep
How many bugs can LMs find & fix in large codebases?
- ai
- ai-agents
- benchmark
- benchmarking
- harbor
- harbor-framework
- +5 more
+12 stars
from 204 · score 2.56
10.apple-aiml-research / ml-rsi-inference-bench
A Long-Horizon Benchmark for Self-Improving Inference Systems
+9 stars
from 126 · score 2.30
11.Gen-Verse / DiscoveryRSI
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
- agent-framework
- agentic-workflow
- aiforscience
- llm-agents
- recursive-self-improvement
+6 stars
from 140 · score 1.95