Compare
Cogito v2.1 vs Kimi K3
Cogito v2.1 (Deep Cogito) and Kimi K3 (Moonshot) compared on benchmarks, pricing, context window, and use-case rankings.
- Kimi K3 ranks higher for coding (97th vs 26th percentile).
| Attribute | Cogito v2.1 | Kimi K3 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | — | 158 |
| Coding | 26 | 97 |
| Math | 13 | 81 |
| Reasoning & Knowledge | 28 | 73 |
| Agentic & Tools | — | 80 |
| Specifications | ||
| Developer | Deep Cogito | Moonshot |
| Family | — | Kimi |
| Released | Nov 19, 2025 | Jul 16, 2026 |
| Parameters | — | 2.8T |
| Availability | Open weights (unrestricted) | Open weights (non-commercial) |
| Context window | — | 1M |
| Price — $/M input | — | $2.55 |
| Price — $/M output | — | $12.75 |
| Inputs | — | text, image, video |
| Outputs | — | text |
| Benchmarks | ||
| AIME 2024/2025 | 73% | 97% |
| GPQA Diamond | 77% | 93% |
| Humanity's Last Exam | 12% | 47% |
| LiveCodeBench | 69% | — |
| MMLU-Pro | 85% | — |
| SciCode | 41% | 60% |
| APEX | — | 39% |
| ARC-AGI | — | 95% |
| ARC-AGI-2 | — | 60% |
| SimpleBench | — | 61% |
| SimpleQA Verified | — | 51% |
| WebDev Arena | — | 1674 |
| WeirdML | — | 83% |
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Frequently asked questions
Which is better for coding, Cogito v2.1 or Kimi K3?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Kimi K3 ranks higher — 97th vs 26th percentile among the models tracked on Model Beat.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.