Benchmark Almanac

Ivo-micro1 ContractBench

Grok 4.7 58.3% leads since Oct 2026 Not in model cards

Models review contracts and return redlines across 350 attorney-written tasks in 35 scenarios and five agreement types. Tasks cover first review and replies to a counterparty.

Scores whether models intervene where several attorneys did, plus a surgicality index of targeted inline edits. Attorneys scored 63.5% on surgicality against 36.6% for the best model.

Made by micro1 with Ivo Released Oct 2026 Law All tasks public Last model added Sep 2026 Scores refreshed 2 Nov 2026
Level
Expert Specialists with years of training, often over hours of work
Scored
Graded by a model A language model scores each response, usually against a rubric.
Answers
Open-ended Free-form text, documents, designs or media judged as a whole.
micro1-research/contract-bench 1 stars Paper Dataset Leaderboard
7
Models scored on its own leaderboard

Grok 4.7 leads with 58.3%

Best score per model from the benchmark's own leaderboard, read on 2 Nov 2026. Where a model ran with several settings or harnesses, we keep its best.

  1. 58.3 Grok 4.7
  2. 58.1 Claude Opus 5.5
  3. 57.1 Kimi K3
  4. 55.0 GLM-5.3
  5. 55.0 Gemini 3.8 Flash
  6. 48.4 DeepSeek-V4-Pro
  7. 45.6 GPT-6 Astra
  1. 1 Grok 4.7 58.3%
  2. 2 Claude Opus 5.5 58.1%
  3. 3 Kimi K3 57.1%
  4. 4 GLM-5.3 55%
  5. 5 Gemini 3.8 Flash 55%
  6. 6 DeepSeek-V4-Pro 48.4%
  7. 7 GPT-6 Astra 45.6%
#ModelScoreSettingDateSource
1 Grok 4.7 58.3% Sep 2026 Official leaderboard
2 Claude Opus 5.5 58.1% Sep 2026 Official leaderboard
3 Kimi K3 57.1% Jul 2026 Official leaderboard
4 GLM-5.3 55% Aug 2026 Official leaderboard
5 Gemini 3.8 Flash 55% Sep 2026 Official leaderboard
6 DeepSeek-V4-Pro 48.4% Apr 2026 Official leaderboard
7 GPT-6 Astra 45.6% Sep 2026 Official leaderboard

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

xAI
Own leaderboard 1 leader
Grok 4.7 58.3%

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Grok 4.7 Kimi K3 DeepSeek-V4-Pro 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) Grok 4.7 DeepSeek-V4-Pro

No lab model card reports it yet

We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark.

More in Law, finance and medicine

All 140 in Law, finance and medicine
  • HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
  • MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy. Qwen 3.8 Max 80.4%
  • HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
  • KBL In use Models answer Korean legal knowledge and reasoning tasks and Korean bar exam questions. It has 7 knowledge tasks, 4 reasoning tasks and 2,510 bar exam items. Solar Pro 4 77.5%
  • KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. Solar Pro 4 93.2%
  • PRBench In use Model answers 1,100 expert-written law and finance questions. LLM judge grades against weighted expert rubrics of 10-30 criteria each. Muse Spark 1.3 61.6%