Who is SOTA in Finance?Crown open.
Financial analysis on private sets from Vals AI. Finance Agent is the primary; Excel modeling (EMB), TaxEval and Tax Agent Bench rank the rest. Most are graded by LLM judges against expert rubrics. Source: Vals AI. As of Nov 3, 2026, Finance is uncrowned on isitsota (methodology v1.0). Crown history, benchmark weights and methodology.
| # | Model | State | Confidence |
|---|---|---|---|
| 1 | QQwen3.8 27B Alibaba / Qwen | Near-SOTA · Finance | medium |
| 1 | MiMistral Large 4 Mistral | #1 in Finance | low |
Best page and recent changes
- Finance (best per dollar): GLM 5.3 Flash and GPT-5.6 Luna and Muse Spark 1.1 and Muse Spark 1.2 are co-SOTA
- Finance (best per dollar): DeepSeek V4 Flash 0731 and GLM 5.3 Flash and GPT-5.6 Luna and GPT-5 Nano and Muse Spark 1.1 and Muse Spark 1.2 are co-SOTA
- Finance (best per dollar): DeepSeek V4 Flash 0731 and GLM 5.3 Flash and GPT-5.6 Luna and GPT-5 Nano and Muse Spark 1.1 and Muse Spark 1.2 are co-SOTA
What can move this crown
- Finance Agent — primary, weight 1 · Source: Vals AI · AI judge (LLM-graded rubric)
- Excel Modeling Benchmark (EMB) — secondary, weight 0.35 · Source: Vals AI · Mixed (exact checks plus LLM-graded rubric)
- TaxEval — secondary, weight 0.35 · Source: Vals AI · AI judge (LLM-graded rubric)
- Tax Agent Bench — secondary, weight 0.35 · Source: Vals AI · AI judge (LLM-graded rubric)
Source: Vals AI for the Vals benchmarks above: proprietary private test sets run by Vals and republished with permission. Only each benchmark's standard harness counts; product-harness runs (Claude Code, Codex and similar) are not matched to base models. Vals is the only source on this board, so after the first holder a crown change needs two consecutive Vals snapshots that agree. A snapshot is a new Vals release of the board, dated the day isitsota first saw it.
Who is SOTA in Finance?
As of Nov 3, 2026, Finance is uncrowned on isitsota (methodology v1.0).
Since when is the Finance crown current?
As of Nov 3, 2026, Finance has an open crown.