AIMultiple / November 2026
Financial Reasoning
Financial numerical reasoning
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
Accuracy (%) / top five in this selection
Full comparison[FRONTIER LEADERBOARDS]
Published financial AI comparisons in their original ranked-chart format. Each view keeps its own study, metric, model versions and evaluation conditions.
Published model evaluations, reviewed November 13, 2026. Protocols and model versions remain separate, and no Finsider product-performance claim or cross-study aggregate score.
AIMultiple / November 2026
Financial numerical reasoning
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
Accuracy (%) / top five in this selection
Full comparisonModel ML / September 2026
Financial calculations
GPT-6 Astra
93.21
Claude Fable 5.1
92.54
Gemini 3.8 Flash
92.39
Reported score (0-100) / published comparison
Full comparisonModel ML / September 2026
Multi-step financial work
Gemini 3.8 Flash
76.33
GPT-6 Astra
72.36
Claude Fable 5.1
60.00
Reported score (0-100) / published comparison
Full comparisonModel ML / September 2026
Financial document retrieval
GPT-6 Astra
86.30
GPT-5.6 Sol
82.96
Gemini 3.8 Flash
81.48
Reported score (0-100) / published comparison
Full comparisonModel ML / September 2026
Cross-document financial evidence
GPT-6 Astra
78.71
GPT-5.6 Sol
76.77
Gemini 3.8 Flash
63.23
Reported score (0-100) / published comparison
Full comparisonAIMultiple / November 2026
Financial Reasoning / open-weight selection
GLM-5.3
89.50
Kimi K3
88.24
DeepSeek V4 Pro 0813
87.39
GLM-5.2
86.13
gpt-oss-120b
81.09
Accuracy (%) / top five in this selection
Full comparisonFinsider deterministic math engine: comparative evaluation pending. These diligence-specific protocols are research plans, not measured scores, and remain separate from the published comparisons above.
Earnings quality evaluation protocolNot yet evaluated Cash proof evaluation protocolNot yet evaluated Working capital evaluation protocolNot yet evaluated Source lineage evaluation protocolNot yet evaluated Document extraction evaluation protocolNot yet evaluated Review readiness evaluation protocolNot yet evaluated