DAYJOB: Accounting: leaderboard

Long-horizon accounting 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 February 2028. 16 models tracked. Updated 16 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Claude Sonnet 5.5Max35.2#19
2Claude Opus 5.5Max34.4#5
3Muse WonderMax30.8#28
4GPT-6 AstraMax30#6
5Claude Fable 5.1Max27.2#15
6GPT-6.1 SolMax25.2#10
7Grok 4.7xHigh20#47
8Gemini 4 ArgonHigh18#12
9Muse Spark 1.3Max18#43
10Kimi K3.1 Pro13.6#29
11Hy4 previewHigh8.4#71
12GLM-5.3Max7.6#68
13DeepSeek V4.1 Flash (1017)Max7.6#41
14Kimi K3Max6#56
15Gemini 3.8 FlashHigh6#36

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

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