Cogito v2 preview - 671B MoE
World-class MoE reasoning approaching superintelligence
This model is not available on Together’s Serverless API.
Pick a supported alternative from the Model Library.
Performance benchmarks
Model | AIME 2025 | GPQA Diamond | HLE | LiveCodeBench | MATH500 | SWE-bench verified |
|---|---|---|---|---|---|---|
Cogito v2 preview - 671B MoE | 69.7% | Related open-source models | Competitor closed-source models | |||
 Claude Fable 5 | 92.6% | 53% | ||||
Claude Opus 5 | 93.2% | 53% | ||||
 GPT-5.6 Sol | 94.1% | 47% | ||||
 Grok 4.5 | 93.1% | 40% |
Related models
