# llm-as-a-verifier/llm-as-a-verifier

LLM-as-a-Verifier is a general-purpose framework that provides fine-grained feedback for any agent without requiring additional training. It achieves SOTA performance across coding, robotics, and medical agentic benchmarks.

Repository: https://github.com/llm-as-a-verifier/llm-as-a-verifier
Canonical: https://ross.abutalabs.com/products/llm-as-a-verifier
Homepage: https://llm-as-a-verifier.com/docs/
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-20T07:01:30+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 10
- inputs: {"age_days": 146, "days_push": 13, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2901, forks 229 (observed 2026-08-28T04:07:28.714860+00:00)

## What it is
A Python framework that uses LLM token logprobs to produce fine-grained verification scores for agent trajectories without additional training. It provides best-of-N selection, pairwise comparison, and progress tracking APIs, and ships agentic benchmarks like Terminal-Bench and SWE-Bench Verified.

## Use cases
- rank candidate solutions from an LLM agent with best-of-N selection
- score agent trajectories step by step for progress tracking
- generate dense reward signals for reinforcement learning
- verify coding agent outputs against custom criteria
- evaluate robotics or medical agent rollouts with image inputs
- run agentic benchmarks like Terminal-Bench and SWE-Bench Verified
- compare two candidate answers pairwise with an LLM judge

## When to choose
- you need fine-grained, calibrated verification scores for agent outputs without training a reward model
- you want test-time scaling via best-of-N selection with a cost-efficient tournament
- you need dense rewards for RLHF-style training of agents
- you want multimodal verification of image or video agent trajectories

## When to avoid
- you need a simple pass/fail test suite rather than probabilistic scoring
- you cannot access an LLM backend that returns token logprobs
- you need fully offline verification with no API or GPU costs
- your evaluation requires deterministic, reproducible ground-truth checks only

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, machine-learning, agent-framework, benchmarking, rag
- domain: large-language-models, machine-learning, developer-tools
- platform: python, cross-platform, cli
- tags: llm-as-a-judge, reward-model, best-of-n-selection, reinforcement-learning-rewards, test-time-scaling, pairwise-comparison, progress-tracking, multimodal-verification, ai-agents

## Member repositories
- llm-as-a-verifier/llm-as-a-verifier (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:28.714860+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 2026-08-30T07:35:10.094074+00:00, confidence not recorded.
  - readme: https://github.com/llm-as-a-verifier/llm-as-a-verifier (fetched 2026-08-28T04:07:28.714860+00:00, sha 0c1da9471a6c)
  - homepage: https://llm-as-a-verifier.com/docs/ (fetched 2026-08-29T09:50:01.978844+00:00, sha de979941de69)
  - site_page: https://llm-as-a-verifier.com/docs/get_started/installation.html (fetched 2026-08-29T09:50:01.988530+00:00, sha 15065a241cdd)
  - site_page: https://llm-as-a-verifier.com/docs/multimodal/image_inputs.html (fetched 2026-08-29T09:50:02.011657+00:00, sha 72d5df7d74ea)
  - site_page: https://llm-as-a-verifier.com/docs/basic_usage/best_of_n_selection.html (fetched 2026-08-29T09:50:01.990804+00:00, sha 478a6ec842df)
  - site_page: https://llm-as-a-verifier.com/docs/basic_usage/pairwise_comparison.html (fetched 2026-08-29T09:50:01.992764+00:00, sha 847be5422938)
  - site_page: https://llm-as-a-verifier.com/docs/basic_usage/progress_tracking.html (fetched 2026-08-29T09:50:01.994591+00:00, sha c7a2e4efc440)
  - site_page: https://llm-as-a-verifier.com/docs/basic_usage/criteria.html (fetched 2026-08-29T09:50:01.996592+00:00, sha af5a4eeaa18f)
  - site_page: https://llm-as-a-verifier.com/docs/benchmarks/running_benchmarks.html (fetched 2026-08-29T09:50:01.998553+00:00, sha 3199fe85b96b)
  - site_page: https://llm-as-a-verifier.com/docs/benchmarks/add_new_benchmark.html (fetched 2026-08-29T09:50:02.009833+00:00, sha faa05618530e)
- Data as of 2026-08-30T08:39:29.467469+00:00.