Legal Benchmarks: Contract Workflows leaderboard

Top 10 by Task pass rate · 27 models listed by the source

chatjudge.ai
Legal Benchmarks: Contract Workflows: top 10 by Task pass rateBars from zero. Joint leaders: Claude Opus 5.5, Claude Fable 5.1 and Muse Spark 1.3, all at 48.4%. Full values at chatjudge.ai.0%10%20%30%40%50%Claude Opus 5.5 (Anthropic), rank 1: 48.4%AClaude Opus 5.548.4%Claude Fable 5.1 (Anthropic), rank 1: 48.4%AClaude Fable 5.148.4%Muse Spark 1.3 (Meta), rank 1: 48.4%MMuse Spark 1.348.4%Claude Opus 5 (Anthropic), rank 4: 45.2%AClaude Opus 545.2%Qwen 3.8 Flash (Alibaba), rank 5: 38.7%QQwen 3.8 Flash38.7%Claude Haiku 5.5 (Anthropic), rank 6: 35.5%AClaude Haiku 5.535.5%Claude Fable 5.2 (Anthropic), rank 7: 32.3%AClaude Fable 5.232.3%Claude Sonnet 5.5 (Anthropic), rank 8: 29.0%AClaude Sonnet 5.529.0%Qwen 3.8 Max (Alibaba), rank 8: 29.0%QQwen 3.8 Max29.0%GPT-6 Astra (OpenAI), rank 10: 25.8%OGPT-6 Astra25.8%
Legal Benchmarks: Contract Workflows: top 10 by Task pass rateBars from zero. Joint leaders: Claude Opus 5.5, Claude Fable 5.1 and Muse Spark 1.3, all at 48.4%. Full values at chatjudge.ai.0%20%40%60%Claude Opus 5.5 (Anthropic), rank 1: 48.4%AClaude Opus 5.548.4%Claude Fable 5.1 (Anthropic), rank 1: 48.4%AClaude Fable 5.148.4%Muse Spark 1.3 (Meta), rank 1: 48.4%MMuse Spark 1.348.4%Claude Opus 5 (Anthropic), rank 4: 45.2%AClaude Opus 545.2%Qwen 3.8 Flash (Alibaba), rank 5: 38.7%QQwen 3.8 Flash38.7%Claude Haiku 5.5 (Anthropic), rank 6: 35.5%AClaude Haiku 5.535.5%Claude Fable 5.2 (Anthropic), rank 7: 32.3%AClaude Fable 5.232.3%Claude Sonnet 5.5 (Anthropic), rank 8: 29.0%AClaude Sonnet 5.529.0%Qwen 3.8 Max (Alibaba), rank 8: 29.0%QQwen 3.8 Max29.0%GPT-6 Astra (OpenAI), rank 10: 25.8%OGPT-6 Astra25.8%