MBABench 2.0
Agents build spreadsheet financial models for 101 tasks written by finance experts. A task passes only if every number matches the reference and the workbook meets a quality bar.
20 agents in their own harnesses at launch. Only one agent passed any of the 20 Hard tasks. Funded by Snorkel Open Benchmarks Grants.
- Released
- October 2026
- Kind
- Finance
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Strongest model tested
- GPT-6 Astra #3 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 12th, 2026
GPT-6 Astra leads with 15.8% among models released by September 2026
Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.
The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
-
Gemini 4 Carbon - Claude Opus 5.5
- GPT-6.1 Sol
- and 13 more
- 1 GPT-6 Astra xhigh 15.8%
- 2 Claude Fable 5.1 max 7.90%
- 3 Claude Opus 5 max 4.00%
- 4 GPT-6-Pro 3.00%
- 5 Qwen 3.8 (variant unspecified) xhigh 1.00%
- 6 Grok 4.6 xhigh 1.00%
- 7 Gemini 3.8 (variant unspecified) high 0%
- 8 Sol (variant unspecified) xhigh 0%
- 9 Kimi K3 max 0%
Source: Official MBABench 2.0 leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 15.8% | xhigh, Codex | Sep 2026 | Official leaderboard |
| 2 | Claude Fable 5.1 | 7.90% | max, Claude Code | Sep 2026 | Official leaderboard |
| 3 | Claude Opus 5 | 4.00% | max, Claude Code | Jul 2026 | Official leaderboard |
| 4 | GPT-6-Pro | 3.00% | ChatGPT | Official leaderboard | |
| 5 | Qwen 3.8 (variant unspecified) | 1.00% | xhigh, Codex | Official leaderboard | |
| 6 | Grok 4.6 | 1.00% | xhigh, Codex | Aug 2026 | Official leaderboard |
| 7 | Gemini 3.8 (variant unspecified) | 0% | high, Codex | Official leaderboard | |
| 8 | Sol (variant unspecified) | 0% | xhigh, ChatGPT for Excel | Official leaderboard | |
| 9 | Kimi K3 | 0% | max, Codex | Jul 2026 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official MBABench 2.0 leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official MBABench 2.0 leaderboard
No lab model card reports it yet
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.
Versions
More in Law, finance and medicine
- MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy.
Qwen 3.8 Max 80.4% - HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
- HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
- FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy.
Ling-3.1-flash 81.7% - KBL In use Models answer Korean legal knowledge and reasoning tasks and Korean bar exam questions. It has 7 knowledge tasks, 4 reasoning tasks and 2,510 bar exam items.
Solar Pro 4 77.5% - KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. Solar Pro 4 93.2%