CorporateBench: leaderboard

An agent extracts and queries facts across corporate document collections of a few hundred to more than 230,000 emails and files; the score is the mean over 3 Fireworks runs of all 128 tasks. It tests retrieval at e-discovery scale rather than drafting legal work product.

Metric: Mean score over 3 runs of 128 tasks (%). Source: fireworks.ai. Saturation forecast: Around July 2027. 12 models tracked. Updated 16 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-6.1 SolMax82.21#10
2GPT-6 AstraMax81.96#6
3GPT-6 SolMax79#26
4Kimi K3.1 ProMax78.45#29
5Gemini 3.8 FlashHigh77.57#36
6Claude Opus 5.5Max75.38#5
7DeepSeek V4.1 FlashMax75.29#62
8DeepSeek V4.1 Flash (1017)Max75.21#41
9Claude Opus 5Max74#20
10Muse Spark OpenMax73#81
11Kimi K3Max72.33#56
12GPT-6 LunaMax71.74#99

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

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