Claude Opus 5.5 tops Artificial Analysis at 58; four new models add 11 Pareto frontier points
ArtificialAnlys · x · 2026-09-24
Artificial Analysis reports the Intelligence Index vs Cost per Task Pareto frontier shifted this week with MiMo-V2.6-Pro, Claude Opus 5.5, GPT-6 Luna, and GPT-6 Sol, adding eleven new frontier points across reasoning efforts (five from GPT-6 Luna, four from Opus 5.5, one each from MiMo-V2.6-Pro and GPT-6 Sol).
Key numbers:
- GPT-6 Luna (max): 37 at $0.068/task
- MiMo-V2.6-Pro: 46 at $0.13/task
- GPT-6 Sol (max): 48 at $1.06/task
- Claude Opus 5.5 (max with fallback): 58 at $5.98/task — now the highest-scoring model
More from Models
- GPT-6 Luna beats GPT-5.6 Sol on HealthBench Professional at ~34x lower cost — BorisMPower · 2026-09-24
- Theory: model 'nerfing' may come from mixed heterogeneous inference hardware, not intent — michellechen · 2026-09-24
- "Please Don't Start This with LLMs": Backlash Against Max Prime-Style Model Naming — scaling01 · 2026-09-24
- Limite 1B 'Violetto': tiny open-source model claims competition-math wins over far larger systems — tensorqt · 2026-09-24
- MentalHealthBench: Frontier Models Improving but Gaps Remain in Context-Seeking — thekaransinghal · 2026-09-24
- OpenThai-SystemOne: An 0.8B Open Model That Answers Typed Decisions With Calibrated Probabilities — lmoroney · 2026-09-24