Atlas

Benchmarks

← All benchmarks

FrontierFinance v3.1 — Sector, Industry, and Macro

Professional Work · 2026-07-06

Sector, Industry, and Macro use-case slice of Samaya AI's FrontierFinance v3.1, containing 38 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 Sol40.9
Claude Fable 538.1
Opus 4.835.2
GPT-5.534.7
GLM-5.234.4
DeepSeek-V4-Pro32.7
Kimi K2.625.6
Gemini 3.1 Pro Preview25.0
Loading Atlas data…