Atlas

Benchmarks

← All benchmarks

FrontierFinance v3.1 — Forward-Looking Information Rubrics

Professional Work · 2026-07-06

Forward-Looking Information rubric-category slice in the official FrontierFinance v3.1 system breakdown, with a reported denominator of 812 rubric criteria. It reports micro-averaged rubric qualification rate within that displayed category.

Top models (higher is better)

ModelScore
Claude Fable 5.149.4
Claude Fable 548.0
GPT-5.6 Sol43.4
Gemini 3.8 Flash40.9
GPT-5.540.7
Gemini 3.6 Flash39.2
Opus 4.838.7
Ling 3.0 Flash Fin38.7
GLM-5.238.2
Kimi K335.5
DeepSeek-V4-Pro29.6
Kimi K2.627.4
Gemini 3.1 Pro Preview25.9
Loading Atlas data…