Atlas

Benchmarks

← All benchmarks

Finance Agent v2 (Vals Multimodal Index component)

Professional Work · 2026-06-10

Finance Agent v2 evaluated on the Vals Multimodal Index subset with its six-tool agent protocol and partial-credit metric.

Top models (higher is better)

ModelScore
Gemini 3.5 Flash58.1
Muse Spark 1.157.1
Claude Opus 556.6
Claude Fable 556.3
Kimi K355.9
GPT-5.6 Luna55.6
Gemini 3.6 Flash55.3
GPT-5.6 Sol55.0
Opus 4.853.9
GPT-5.6 Terra52.6
Sonnet 552.0
GPT-5.551.8
Opus 4.751.5
Sonnet 4.651.0
Grok 4.548.8
MiniMax M348.0
GPT-5.4 Mini45.4
Kimi K2.644.9
Gemini 3.1 Pro Preview43.0
Gemini 3 Flash Preview42.5
Qwen3.7-Plus41.2
Qwen3.6 Plus (2026-04-02)40.9
GPT-5.4 Nano38.2
Grok 4.337.8
MiMo-V2.537.6
Mistral Medium 3.531.5
Haiku 4.531.0
Gemini 3.1 Flash-Lite Preview30.1
Grok 4.2028.6
Loading Atlas data…