DAYJOB: Law: leaderboard

Long-horizon legal assignments from a brief request and a workspace of files, graded by an agent judge against an expert rubric; the score is the share of attempts meeting at least 95% of criteria. Surge AI supplied these results before publishing the board and has not stated the task count.

Metric: Attempts meeting at least 95% of rubric criteria (%). Source: fireworks.ai. Saturation forecast: Around July 2028. 16 models tracked. Updated 16 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-6 AstraMax36.9#6
2Muse WonderMax36.6#28
3GPT-6.1 SolMax31.8#10
4Grok 4.7xHigh27.6#47
5Claude Sonnet 5.5Max27#19
6Claude Fable 5.1Max26.5#15
7Claude Opus 5.5Max25.1#5
8Kimi K3.1 Pro23.9#29
9Muse Spark 1.3Max22.8#43
10Qwen 3.8 MaxxHigh16.9#59
11Gemini 4 ArgonHigh9.9#12
12Hy4 previewHigh9.9#71
13GLM-5.3Max6.2#68
14DeepSeek V4.1 Flash (1017)Max6.2#41
15Mistral Large 4High4.5#137

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon.

Interactive version: theaggregate.ai/benchmark?slug=dayjob-law · How It Works · Data refreshed daily, snapshot 2026-11-16.