Kimi K3 vs MiniMax-M2.1
Kimi K3 (Moonshot) and MiniMax-M2.1 (MiniMax) compared on benchmarks, pricing, context window, and use-case rankings.
- MiniMax-M2.1 is cheaper on input tokens — $0.30 vs $2.10 per 1M.
- Kimi K3 has a larger context window (1M vs 205K tokens).
- Kimi K3 ranks higher for coding (97th vs 35th percentile).
| Attribute | Kimi K3 | MiniMax-M2.1 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 158 | — |
| Coding | 97 | 35 |
| Math | 80 | 22 |
| Reasoning & Knowledge | 73 | 55 |
| Agentic & Tools | 80 | 34 |
| Specifications | ||
| Developer | Moonshot | MiniMax |
| Family | Kimi | MiniMax |
| Released | Jul 16, 2026 | Dec 23, 2025 |
| Parameters | 2.8T | 229B |
| Availability | Open weights (non-commercial) | Open weights (restricted use) |
| Context window | 1M | 205K |
| Price — $/M input | $2.10 | $0.30 |
| Price — $/M output | $10.95 | $1.20 |
| Inputs | text, image, video | text |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 97% | 83% |
| APEX | 39% | — |
| ARC-AGI | 95% | — |
| ARC-AGI-2 | 60% | — |
| GPQA Diamond | 93% | 83% |
| Humanity's Last Exam | 47% | 23% |
| SciCode | 60% | 41% |
| SimpleBench | 61% | — |
| SimpleQA Verified | 51% | — |
| WebDev Arena | 1674 | 1387 |
| WeirdML | 83% | — |
| LiveCodeBench | — | 81% |
| MMLU-Pro | — | 88% |
| Terminal-Bench | — | 37% |
| τ²-bench | — | 85% |
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 cheaper, Kimi K3 or MiniMax-M2.1?
MiniMax-M2.1 is cheaper on input tokens at $0.30 per million, versus $2.10 (representative OpenRouter pricing).
Which has a larger context window, Kimi K3 or MiniMax-M2.1?
Kimi K3 supports up to 1M tokens, compared with 205K for the other.
Which is better for coding, Kimi K3 or MiniMax-M2.1?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Kimi K3 ranks higher — 97th vs 35th 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.