FinED-Bench - Financial Reasoning Errors: leaderboard

Metric: F1 (%; financial reasoning errors: conflicting expression, time contradiction, numerical inconsistency, calculation error, clause conflict; a predicted error counts as correct when the extracted sentence matches or contains the annotated sentence and the error type is classified correctly; the paper's error-detection prompt over each document, reasoning models with thinking on unless marked no thinking). Source: arxiv.org. Saturation forecast: Estimated already saturated. 11 models tracked.

Top models

#ModelScore
1GPT-4o38
2Qwen 3 14B29.1
3Qwen 3 8B27.96
4Qwen 3 14B (Non-reasoning)16.63
5DeepSeek R1 0528 Qwen3 8B13.71
6GPT-4o Mini10.98
7Qwen 3 8B (Non-reasoning)8.6
8Qwen 2.5 7B Instruct3.79
9GPT-3.5 Turbo2.41

Interactive version: theaggregate.ai/benchmark?slug=fined-bench-financial-reasoning-errors · How It Works · Data refreshed daily, snapshot 2026-09-26.