Legal Benchmarks: Contract Workflows leaderboard (Nov 2026): AI model scores
As of Nov 2026, the highest reported score on Legal Benchmarks: Contract Workflows is shared by Claude Opus 5.5 (Anthropic), Claude Fable 5.1 (Anthropic) and Muse Spark 1.3 (Meta) at 48.4%, per Legal Benchmarks.
Source: Legal Benchmarks leaderboard ↗ · Leaderboard dated Nov 2026 · Last checked 17 Nov 2026
Contract Workflows
Contract drafting tasks written by lawyers, each run twice; a task passes only if every criterion is met both times.
Loading chart…
Each square is one model, marked with its provider’s initial. Higher is better; further left costs less per task.
Joint leaders: Claude Opus 5.5 (Anthropic), Claude Fable 5.1 (Anthropic) and Muse Spark 1.3 (Meta), all at 48.4%.
Task pass rate, highest first. Position is the source’s published rank.
- 1Claude Opus 5.5 Anthropic48.4%
- 1Claude Fable 5.1 Anthropic48.4%
- 1Muse Spark 1.3 Meta48.4%
- 4Claude Opus 5 Anthropic45.2%
- 5Qwen 3.8 Flash Alibaba38.7%
- 6Claude Haiku 5.5 Anthropic35.5%
- 7Claude Fable 5.2 Anthropic32.3%
- 8Claude Sonnet 5.5 Anthropic29.0%
- 8Qwen 3.8 Max Alibaba29.0%
- 10GPT-6 Astra OpenAI25.8%
- 10GPT-6.1 Sol OpenAI25.8%
- 10Gemini 3.8 Flash Google25.8%
- 10Grok 4.6 xAI25.8%
- 10Mistral Large 4 Mistral25.8%
- 10Gemini 4 Argon Google25.8%
- 16GPT-5.6 Sol OpenAI22.6%
- 16Kimi K3 Moonshot22.6%
- 16DeepSeek V4 Flash DeepSeek22.6%
- 16GLM-5.3 Flash Z.ai22.6%
- 20GPT-5.6 Luna OpenAI19.4%
- 20DeepSeek V4 Pro DeepSeek19.4%
- 20GLM-5.3 Z.ai19.4%
- 23GPT-5.6 Terra OpenAI16.1%
- 23Claude Sonnet 5 Anthropic16.1%
- 25GPT-6.1 Terra OpenAI12.9%
- 25MiniMax M3 MiniMax12.9%
- 27Mistral Medium 3.5 Mistral9.7%
| 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 Fable 5.2 | Anthropic | 32.3% | 88.7% | 90.9% | $2.98 |
| 8 | Claude Sonnet 5.5 | Anthropic | 29.0% | 85.3% | 91.1% | $0.98 |
| 8 | Qwen 3.8 Max | Alibaba | 29.0% | 32.2% | 64.2% | $0.39 |
| 10 | GPT-6 Astra | OpenAI | 25.8% | 87.1% | 91.9% | $1.13 |
| 10 | GPT-6.1 Sol | OpenAI | 25.8% | 86.3% | 90.8% | $0.11 |
| 10 | Gemini 3.8 Flash | 25.8% | 65.9% | 76.4% | $0.22 | |
| 10 | Grok 4.6 | xAI | 25.8% | 62.2% | 76.8% | $0.28 |
| 10 | Mistral Large 4 | Mistral | 25.8% | 30.6% | 63.4% | $0.090 |
| 10 | Gemini 4 Argon | 25.8% | 30.5% | 60.3% | $0.26 | |
| 16 | GPT-5.6 Sol | OpenAI | 22.6% | 84.8% | 89.2% | $0.18 |
| 16 | Kimi K3 | Moonshot | 22.6% | 78.8% | 84.7% | $0.26 |
| 16 | DeepSeek V4 Flash | DeepSeek | 22.6% | 57.1% | 73.4% | $0.010 |
| 16 | GLM-5.3 Flash | Z.ai | 22.6% | 56.0% | 67.8% | $0.020 |
| 20 | GPT-5.6 Luna | OpenAI | 19.4% | 80.9% | 86.1% | $0.020 |
| 20 | DeepSeek V4 Pro | DeepSeek | 19.4% | 78.6% | 88.3% | $0.080 |
| 20 | GLM-5.3 | Z.ai | 19.4% | 68.1% | 81.9% | $0.090 |
| 23 | GPT-5.6 Terra | OpenAI | 16.1% | 81.2% | 86.0% | $0.14 |
| 23 | Claude Sonnet 5 | Anthropic | 16.1% | 80.1% | 86.9% | $0.36 |
| 25 | GPT-6.1 Terra | OpenAI | 12.9% | 82.9% | 80.1% | $0.070 |
| 25 | MiniMax M3 | MiniMax | 12.9% | 80.1% | 83.4% | $0.030 |
| 27 | Mistral Medium 3.5 | Mistral | 9.7% | 47.7% | 75.0% | $0.32 |
Source: Legal Benchmarks · leaderboard dated Nov 2026 · checked 17 Nov 2026
Free to use on your site, blog or newsletter. Please keep the “via chatjudge.ai” credit and the source link under the chart. The chart updates itself when we refresh the scores.
Citation
Legal Benchmarks: Contract Workflows, task pass rate: Claude Opus 5.5 (Anthropic), Claude Fable 5.1 (Anthropic) and Muse Spark 1.3 (Meta) tied for the top reported score at 48.4%. Original source: Legal Benchmarks, https://www.legalbenchmarks.ai/leaderboard/models, leaderboard dated Nov 2026. Via ChatJudge: https://chatjudge.ai/benchmarks/legal/legal-benchmarks-contracts, checked 17 Nov 2026.
Other published views: Substance vs form
- Anthropic
- OpenAI
- xAI
- Meta
- DeepSeek
- Alibaba
- Z.ai
- Moonshot
- MiniMax
- Mistral
Methodology and caveats
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
- 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.
Run by Legal Benchmarks. Leaderboard dated Nov 2026. Last checked 17 Nov 2026.
November 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.
Source: Legal Benchmarks leaderboard ↗ · How the judge was calibrated (Clavia) ↗
Results from published AI leaderboards. Compare models within each benchmark; scores from different tests aren’t directly comparable. How we collect these results
Joint leaders: Claude Opus 5.5 (Anthropic), Claude Fable 5.1 (Anthropic) and Muse Spark 1.3 (Meta). Try prompts for Claude → Try prompts for Muse →
Questions people ask
Which AI has the highest reported score on Legal Benchmarks: Contract Workflows?
As of Nov 2026, the highest reported score on Legal Benchmarks: Contract Workflows is shared by Claude Opus 5.5 (Anthropic), Claude Fable 5.1 (Anthropic) and Muse Spark 1.3 (Meta) at 48.4%, per Legal Benchmarks.
What does Legal Benchmarks: Contract Workflows measure?
Contract drafting tasks written by lawyers, each run twice; a task passes only if every criterion is met both times. It is run by Legal Benchmarks.
What does the Legal Benchmarks: Contract Workflows score mean?
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.
How recent are these Legal Benchmarks: Contract Workflows results?
Legal Benchmarks: Contract Workflows: leaderboard dated Nov 2026; we last checked it on 17 Nov 2026.
What do the joint top-scoring models cost to run on Legal Benchmarks: Contract Workflows?
On Legal Benchmarks: Contract Workflows, Claude Opus 5.5 costs $1.47, Claude Fable 5.1 costs $1.50 and Muse Spark 1.3 costs $0.20 (cost per task), as published by Legal Benchmarks. That is API cost on the benchmark’s own tasks, not a subscription price.
Can I compare Legal Benchmarks: Contract Workflows scores with other benchmarks?
Not directly. Each leaderboard uses its own tasks, settings and scoring, so compare models within one benchmark. ChatJudge does not run the tests; we copy the published scores with a link to the source.
