Atlas

Benchmarks

← All benchmarks

SOLO Bench Medium

Chat & Writing · 2025-05-01

SOLO Bench Medium increases the SOLO Bench task to 500 unique constrained sentences. It is substantially harder because the model must maintain more long-output constraints without repeating list words.

Top models (higher is better)

ModelScore
Gemini 2.5 Pro Preview 03-2557.8
Claude 3.7 Sonnet13.6
DeepSeek-R111.8
o38.2
GPT-4.55.8
Grok 33.8
Loading Atlas data…