Legal Benchmarks: Contract Workflows leaderboard (Oct 2026): AI model scores

Name: Legal Benchmarks: Contract Workflows leaderboard: AI model scores
Creator: Legal Benchmarks

As of Oct 2026, the highest reported Mistral score on Legal Benchmarks: Contract Workflows is Mistral Large 4 (Mistral) at 25.8%, #9 on that leaderboard, per Legal Benchmarks.

What it measures

Contract drafting tasks written by lawyers, each run twice; a task passes only if every criterion is met both times.

Lawyer-authored contract drafting tasks with native source documents. A task passes only if every applicable criterion is met in both of the model’s two attempts; form is scored separately.

What the score means

Task pass rate: tasks meeting every criterion in both attempts

Share of contract tasks that satisfy every applicable criterion in both of the model’s independent attempts.

Results from published AI leaderboards. Compare models within each benchmark; scores from different tests aren’t directly comparable. How we collect these results

Scores by model

Run by Legal Benchmarks. Leaderboard dated Oct 2026. Last checked 22 Oct 2026.

Highlight a provider: Anthropic OpenAI Google xAI Meta DeepSeek Alibaba Z.ai Moonshot MiniMax Mistral

Highlighting Mistral models. Other providers are dimmed. Show all providers

Anthropic
OpenAI
Google
xAI
Meta
DeepSeek
Alibaba
Z.ai
Moonshot
MiniMax
Mistral

Task pass rate: Share of contract tasks that satisfy every applicable criterion in both of the model’s independent attempts.
Criteria pass rate: Share of applicable contract criteria the model meets, as published.
Form: Share of applicable binary form checks (clarity, length, structure) passed in both independent attempts.
Cost per task (USD): Cost per task, as published.

October 2026 round. It ranks by task pass rate, so it is not comparable with the September round (Criterion Pass²) we charted before. Provider names follow ours (Qwen is listed under Alibaba). Latency is on the source page.

All scores

Legal Benchmarks: Contract Workflows scores, Mistral models highlighted
Rank	Model	Provider	Task pass rate	Criteria pass rate	Form	Cost per task (USD)
1	Claude Opus 5.5	Anthropic	48.4%	91.7%	93.9%	$1.47
1	Claude Fable 5.1	Anthropic	48.4%	90.7%	89.7%	$1.50
1	Muse Spark 1.3	Meta	48.4%	87.4%	87.8%	$0.20
4	Claude Opus 5	Anthropic	45.2%	90.1%	90.8%	$0.90
5	Qwen 3.8 Flash	Alibaba	38.7%	49.1%	67.7%	$0.030
6	Claude Haiku 5.5	Anthropic	35.5%	76.9%	83.1%	$0.16
7	Claude Sonnet 5.5	Anthropic	29.0%	85.3%	91.1%	$0.98
7	Qwen 3.8 Max	Alibaba	29.0%	32.2%	64.2%	$0.39
9	GPT-6 Astra	OpenAI	25.8%	87.1%	91.9%	$1.13
9	GPT-6.1 Sol	OpenAI	25.8%	86.3%	90.8%	$0.11

Show 14 more rows

Rank	Model	Provider	Task pass rate	Criteria pass rate	Form	Cost per task (USD)
9	Gemini 3.8 Flash	Google	25.8%	65.9%	76.4%	$0.22
9	Grok 4.6	xAI	25.8%	62.2%	76.8%	$0.28
9	Mistral Large 4	Mistral	25.8%	30.6%	63.4%	$0.090
14	GPT-5.6 Sol	OpenAI	22.6%	84.8%	89.2%	$0.18
14	Kimi K3	Moonshot	22.6%	78.8%	84.7%	$0.26
14	DeepSeek V4 Flash	DeepSeek	22.6%	57.1%	73.4%	$0.010
14	GLM-5.3 Flash	Z.ai	22.6%	56.0%	67.8%	$0.020
18	GPT-5.6 Luna	OpenAI	19.4%	80.9%	86.1%	$0.020
18	DeepSeek V4 Pro	DeepSeek	19.4%	78.6%	88.3%	$0.080
18	GLM-5.3	Z.ai	19.4%	68.1%	81.9%	$0.090
21	GPT-5.6 Terra	OpenAI	16.1%	81.2%	86.0%	$0.14
21	Claude Sonnet 5	Anthropic	16.1%	80.1%	86.9%	$0.36
23	MiniMax M3	MiniMax	12.9%	80.1%	83.4%	$0.030
24	Mistral Medium 3.5	Mistral	9.7%	47.7%	75.0%	$0.32

Source: Legal Benchmarks leaderboard ↗ · How the judge was calibrated (Clavia) ↗

Best-ranked Mistral model here: Mistral Large 4 (Mistral). Browse prompts for any model →

Prompts for this kind of work

Copy-ready prompts from our library that match what Legal Benchmarks: Contract Workflows tests. Run them on your own material to compare models.

ReviewsClaudeCompare two documents clause by clauseChecking a filled-in contract or proposal against its template.View prompt ProposalsChatGPTClarify commercial termsPricing, commission or partnership fees are being misread.View prompt