Financial Reasoning
Multi-step quantitative questions with financial context and numerical answers.
AIMultiple / November 2026 / published research
Evaluation setup
AIMultiple evaluated the 238-question hard subset of FinanceReasoning (Tang et al.) with chain-of-thought prompting, model-based answer extraction, and a 0.2% relative numerical tolerance. Models added from September through November 2026 ran through OpenRouter, while the publisher notes that Opus 5.5 ran in a different execution setup. These are single publisher-reported runs, not Finsider runs, and repeated-run reliability has not been established.
Reading this comparison
Ranks compare displayed scores only within this named evaluation and selected model roster. Ties share a rank. Different benchmarks are not combined into an overall ranking. A model omitted for lack of a published result is not assigned a zero. A newer release is not automatically better on every task.
Boundaries
A benchmark answer score does not establish a model's readiness to deliver a financial diligence engagement. It does not measure CPA sign-off, evidence retention, access controls, or performance on your transaction documents.
Provenance
AIMultiple results compiled November 13, 2026, from the publisher's November 10 update. Model ML results compiled September 14, 2026. Evaluations were performed by the named publishers, not Finsider. CSV downloads record model versions, configurations, sources, and any arithmetic derivation. No comparable result for Finsider's deterministic math engine is available in these sources, so the engine is not ranked.
Performance Comparison
Accuracy (%)
Claude Opus 5.5
91.60
Claude Fable 5.2
91.60
Muse Wonder
91.60
Gemini 4 Argon
90.76
GPT-6.1 Sol Pro
90.34
Gemini 4 Carbon
90.34
GPT-6.1 Sol
89.92
Kimi K3.1 Pro
89.50
GLM-5.3
89.50
Claude Sonnet 5.5
89.08
DeepSeek V4.1 Flash 1017
88.66
Grok 4.7
88.24
Qwen3.8 Max 0902
88.24
GPT-6 Astra
87.39
Claude Haiku 5.5
85.71
The latest release from each major model family in the same 99-model, 238-question evaluation, plus Muse Wonder, which ties for the top score. This is not the full publisher roster, and earlier versions such as GPT-5.6 Sol Pro at 90.76 remain in the source. One question moves a score by about 0.42 points, so 91.60 is 218 correct and 89.08 is 212 correct.
Rank uses displayed scores, and ties share rank. Bars use a 0-100 scale. No confidence intervals are available in the cited results, so small differences should not be interpreted as statistically established superiority.
Source: AIMultiple / November 2026