HELM TORR - Fin Qa - Robustness Leaderboard · The Aggregate

HELM TORR - Fin Qa - Robustness: leaderboard

Metric: Robustness (0-100). Source: crfm.stanford.edu. 14 models tracked.

Top models

#	Model	Score
1	Llama 3.1 8B Instruct	63
2	Gemini 1.5 Pro (002)	59
3	Gemini 1.5 Flash (002)	57
4	Claude 3.5 Sonnet (20241022)	56
5	GPT-4o (2024-11-20)	55
6	Mistral 7B Instruct (v0.3)	51
7	DeepSeek V3	51
8	Qwen 2 72B Instruct	51
9	Claude 3.5 Haiku (20241022)	50
10	Llama 3.1 70B Instruct	49
11	Llama 3.1 405B Instruct	49
12	GPT-4o Mini (2024-07-18)	47

Interactive version: theaggregate.ai/benchmark?slug=helm-torr-fin-qa-robustness · How It Works · Data refreshed daily, snapshot 2026-09-19.