Best AI for financial analysis (Oct 2026)
As of 19 Oct 2026, the highest reported score on Finance Agent is Claude Opus 5.5 (Anthropic) at 67.85%, per Vals AI. As of 12 Aug 2026, the highest reported score on CorpFin v2 is Claude Opus 5 (Anthropic) at 73.19%, per Vals AI. The source no longer updates this leaderboard. The leaders differ across these benchmarks, so check the one closest to your work.
Results from published AI leaderboards. Compare models within each benchmark; scores from different tests aren’t directly comparable. How we collect these results
Finance Agent
Entry-level financial analyst work: answering difficult questions on public company filings. Run by Vals AI. Leaderboard dated 19 Oct 2026. Last checked 21 Oct 2026.
- Anthropic
- OpenAI
- xAI
- Meta
- DeepSeek
- Z.ai
- Moonshot
- MiniMax
- Mistral
- Xiaomi
- Other
Full Finance Agent leaderboard: every model, all metrics and the table →
CorpFin v2
Understanding long-context credit agreements (private benchmark). Run by Vals AI. Leaderboard dated 12 Aug 2026 (no longer updated by the source). Last checked 21 Oct 2026.
- Anthropic
- OpenAI
- xAI
- Meta
- Alibaba
- Z.ai
- Moonshot
- MiniMax
- Other
Full CorpFin v2 leaderboard: every model, all metrics and the table →
What these benchmarks tell you
- Finance Agent: how often a model gets the correct final answer to entry-level financial analyst questions on public company (SEC) filings, including retrieval, calculations and modelling, plus the average cost per test.
- CorpFin: how well a model answers questions about long credit agreements. The source no longer updates it, so newer models may be missing.
What they don’t tell you
- Neither benchmark scores your own books, forecasts or private company data.
- A correct answer on a filing question is not investment advice, and these scores say nothing about returns.
Prompts for financial analysis
Run the same prompt on your own material with two models and compare the results.
Questions people ask
Which AI has the highest reported score for financial analysis?
As of 19 Oct 2026, the highest reported score on Finance Agent is Claude Opus 5.5 (Anthropic) at 67.85%, per Vals AI. As of 12 Aug 2026, the highest reported score on CorpFin v2 is Claude Opus 5 (Anthropic) at 73.19%, per Vals AI. The source no longer updates this leaderboard. The leaders differ across these benchmarks, so check the one closest to your work.
How recent are these results?
Finance Agent: leaderboard dated 19 Oct 2026; we last checked it on 21 Oct 2026. CorpFin v2: leaderboard dated 12 Aug 2026, no longer updated by the source; we last checked it on 21 Oct 2026.
What does the top-scoring model cost to run on these tests?
On Finance Agent, Claude Opus 5.5 costs $8.91 (cost per test), as published by Vals AI. That is API cost on the benchmark’s own tasks, not a subscription price.
Who runs these benchmarks?
Finance Agent is run by Vals AI. CorpFin v2 is run by Vals AI. ChatJudge does not run the tests; we copy the published scores with a link to the source.
What don't these benchmarks tell you about financial analysis?
Neither benchmark scores your own books, forecasts or private company data. A correct answer on a filing question is not investment advice, and these scores say nothing about returns.