# EvolvingLMMs-Lab/lmms-eval

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

Repository: https://github.com/EvolvingLMMs-Lab/lmms-eval
Canonical: https://ross.abutalabs.com/products/lmms-eval
Homepage: https://www.lmms-lab.com
Language: Python
License: NOASSERTION
License Family: other
Topics: agi, evaluation, large-language-models, multimodal, audio-evaluation, benchmark, llm-evaluation, video-understanding, vision-language-model, vlm, multimodal-evaluation
Last push: 2026-08-26T18:30:53+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 78, longevity 64
- inputs: {"age_days": 909, "days_push": 7, "days_rel": 70, "gap_med": 40, "n_releases_24m": 16}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4377, forks 647 (observed 2026-08-28T04:08:46.886483+00:00)

## What it is
lmms-eval is a unified Python framework for evaluating large multimodal models across text, image, video, and audio tasks, with 100+ benchmarks and 30+ model integrations. It emphasizes reproducible, efficient, and trustworthy evaluation pipelines for frontier model research.

## Use cases
- evaluate a vision-language model on standard benchmarks
- compare multimodal model scores reproducibly across teams
- benchmark video understanding models
- run audio evaluation on large multimodal models
- measure LMM performance across image, video, and audio tasks
- set up a unified eval pipeline for model releases

## When to choose
- you need reproducible multimodal benchmark numbers
- you want one toolkit covering text, image, video, and audio evals
- you are a research lab evaluating frontier LMMs at scale

## When to avoid
- you only need text-only LLM evaluation (lm-eval-harness may suffice)
- you need a lightweight ad-hoc metric script rather than a full harness
- you require a commercial benchmarking service with hosted infrastructure

## Facets
- artifact type: framework
- maturity: active
- function: benchmarking, machine-learning, llm-inference, testing
- domain: large-language-models, machine-learning, computer-vision, artificial-intelligence
- platform: python, cross-platform
- tags: multimodal-evaluation, vision-language-models, vlm, llm-evaluation, benchmarks, video-understanding, audio-evaluation, audio, video, gpu, linux

## Member repositories
- EvolvingLMMs-Lab/lmms-eval (main) score 85

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:46.886483+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:21:19.198301+00:00, confidence not recorded.
  - readme: https://github.com/EvolvingLMMs-Lab/lmms-eval (fetched 2026-08-28T04:08:46.886483+00:00, sha 1a0c2b0a87ae)
  - homepage: https://www.lmms-lab.com (fetched 2026-08-29T09:09:33.762689+00:00, sha 77429eb7a494)
  - site_page: https://www.lmms-lab.com/about (fetched 2026-08-29T09:09:33.771938+00:00, sha 14cba1c6f595)
  - registry_pypi: https://pypi.org/pypi/lmms-eval/json (fetched 2026-08-29T09:09:33.773887+00:00, sha 83285aaeb88b)
- Data as of 2026-08-30T08:39:29.467469+00:00.