Atlas

Benchmarks

← All benchmarks

FrontierFinance v3.1 — Company Research

Professional Work · 2026-07-06

Company Research use-case slice of Samaya AI's FrontierFinance v3.1, containing 32 of the 220 public queries. It reports rubric qualification rate macro-averaged across queries in the slice.

Top models (higher is better)

ModelScore
GPT-5.6 Sol42.1
Claude Fable 540.5
GPT-5.539.7
Opus 4.838.9
GLM-5.238.5
Kimi K2.633.3
DeepSeek-V4-Pro32.1
Gemini 3.1 Pro Preview29.7
Loading Atlas data…