Fino1-14B — benchmark results

TheFinAI's financial-reasoning fine-tune of Qwen2.5 14B Instruct, trained on FinQA-derived reasoning paths. Provider: Other. Released 2025-03-28. Access: Open.

Unified ELO 1533 ± 39, rank #677 of 1776 rated models, from 7 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open FinLLM Reasoning - FinQA74.18Accuracy (%)100
Open FinLLM Reasoning - XBRL-Math87.78Accuracy (%)100
Open FinLLM Reasoning58.1Accuracy (%)76
Open FinLLM Reasoning - DM-Simplong55Accuracy (%)66
Open FinLLM Reasoning - DM-Complong27.33Accuracy (%)60
StakeBench9.6Agg (self-reported)35.7
Fin-RATE13.13Macro Accuracy (self-reported)33.3

Interactive version: theaggregate.ai/model?slug=fino1-14b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.