Mercor APEX-Accounting - Pass@1: leaderboard
APEX-Accounting: 100 professional month-end-close tasks across ten held-out company worlds, 1, 475 rubric criteria; a separate eleventh world is public. Native Loop-agent results. Pass@1 and mean criterion/rubric score remain separate metrics; no strongest-harness selection. Criterion-level Met/NotMet LM grading includes a scattergun penalty. The source states five-million-token/500-step limits, step retries and at most three failed-trajectory reruns. Its k=4 criterion means and separately described eight-run pass curves must not be treated as one identical repeated-trial population; native configuration remains retained. Exact native effort, API/EAP identity and score configuration remain per observation. Missing/failure and repeated-trial policies are not inferred from display sample counts. Metric: Pass@1 (%). Source: https://www.mercor.com/apex/apex-accounting-leaderboard/
Metric: Pass@1 (%). Source: www.mercor.com. Saturation forecast: Around 2031. 50 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 4 Argon | High | 23.8 | #14 |
| 2 | Gemini 4 Carbon | High | 22.5 | #3 |
| 3 | Claude Fable 5.2 | Max | 22.5 | #1 |
| 4 | Muse Wonder | Max | 21.3 | #31 |
| 5 | Gemini 4 Hydrogen | Mercor Accounting run: source-id=gemini/gemini-4-hydrogen-eap, access=EAP | 20 | #13 |
| 6 | Claude Fable 5.1 | Max | 19.3 | #17 |
| 7 | Claude Sonnet 5.5 | Max | 19 | #21 |
| 8 | Claude Opus 5.5 | Max | 18.3 | #7 |
| 9 | Claude Opus 5 | Max | 17.8 | #23 |
| 10 | Kimi K3.1 Pro | Max | 17.2 | #32 |
| 11 | GPT-6.1 Terra | Max | 16.8 | #22 |
| 12 | Muse Spark 1.3 | Max | 16.5 | #45 |
| 13 | Gemini 3.8 Flash | High | 15.5 | #39 |
| 14 | Claude Haiku 5.5 | Max | 15.3 | #76 |
| 15 | Grok 4.5 | High | 14.5 | #91 |
No result here: #2 GPT-6.2 Astra, #6 GPT-6.2 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mercor-apex-accounting-pass-1 · How It Works · Data refreshed daily, snapshot 2026-11-17.