open-compass Goto Github PK

.github

ada-leval

The official implementation of "Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks"

anah

[ACL 2024] ANAH: Analytical Annotation of Hallucinations in Large Language Models

botchat

Evaluating LLMs' multi-round chatting capability via assessing conversations generated by two LLM instances.

code-evaluator

A multi-language code evaluation tool.

codebench

criticbench

A comprehensive benchmark for evaluating critique ability of LLMs

devbench

A Comprehensive Benchmark for Software Development.

evalplus

EvalPlus for rigourous evaluation of LLM-synthesized code

human-eval

Code for the paper "Evaluating Large Language Models Trained on Code"

lawbench

Benchmarking Legal Knowledge of Large Language Models

mathbench

[ACL 2024 Findings] MathBench: A Comprehensive Multi-Level Difficulty Mathematics Evaluation Dataset

mixtralkit

A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI

mmbench

Official Repo of "MMBench: Is Your Multi-modal Model an All-around Player?"

opencompass

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

openfindata

pytorch_sphinx_theme

Sphinx Theme for OpenCompass - Modified from PyTorch

t-eval

[ACL2024] T-Eval: Evaluating Tool Utilization Capability of Large Language Models Step by Step

vlmevalkit

Open-source evaluation toolkit of large vision-language models (LVLMs), support GPT-4v, Gemini, QwenVLPlus, 50+ HF models, 20+ benchmarks