Compare
Kimi K3 vs MiniMax-M2
Add, remove, or swap models to compare them side by side.
| Attribute | Kimi K3 | MiniMax-M2 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 158 | — |
| Coding | 97 | 24 |
| Math | 80 | 17 |
| Reasoning & Knowledge | 73 | 15 |
| Agentic & Tools | 72 | 29 |
| Specifications | ||
| Developer | Moonshot | MiniMax |
| Family | Kimi | MiniMax |
| Released | Jul 16, 2026 | Oct 27, 2025 |
| Parameters | 2.8T | 229B |
| Availability | Open weights (non-commercial) | Open weights (unrestricted) |
| 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% | 78% |
| APEX | 51% | — |
| ARC-AGI | 95% | — |
| ARC-AGI-2 | 60% | — |
| GPQA Diamond | 93% | 78% |
| Humanity's Last Exam | 47% | 14% |
| SciCode | 60% | 36% |
| SimpleBench | 61% | — |
| SimpleQA Verified | 51% | — |
| WebDev Arena | 1674 | 1298 |
| WeirdML | 83% | — |
| LiveCodeBench | — | 83% |
| MMLU-Pro | — | 82% |
| Terminal-Bench | — | 30% |
| τ²-bench | — | 87% |
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.
Popular comparisons
- Claude Fable 5 vs GPT-6 Astra
- GPT-6 Astra vs Kimi K3
- Gemini 3.7 Flash vs GPT-6 Astra
- GPT-6 Astra vs Grok 4.6
- DeepSeek-V4-Pro-0813 vs GPT-6 Astra
- GPT-6 Astra vs Qwen 3.7 Max
- GPT-6 Astra vs Muse Spark
- Claude Fable 5 vs Kimi K3
- Claude Fable 5 vs Gemini 3.7 Flash
- Claude Fable 5 vs Grok 4.6
- Claude Fable 5 vs DeepSeek-V4-Pro-0813
- Claude Fable 5 vs Qwen 3.7 Max
- Claude Fable 5 vs Muse Spark
- Gemini 3.7 Flash vs Kimi K3
- Grok 4.6 vs Kimi K3
- DeepSeek-V4-Pro-0813 vs Kimi K3
- Kimi K3 vs Qwen 3.7 Max
- Kimi K3 vs Muse Spark
- Gemini 3.7 Flash vs Grok 4.6
- DeepSeek-V4-Pro-0813 vs Gemini 3.7 Flash
- Gemini 3.7 Flash vs Qwen 3.7 Max
- Gemini 3.7 Flash vs Muse Spark
- DeepSeek-V4-Pro-0813 vs Grok 4.6
- Grok 4.6 vs Qwen 3.7 Max
- Grok 4.6 vs Muse Spark
- DeepSeek-V4-Pro-0813 vs Qwen 3.7 Max
- DeepSeek-V4-Pro-0813 vs Muse Spark
- Muse Spark vs Qwen 3.7 Max
- Claude Fable 5 vs Claude Opus 5
- GPT-5.6 Sol vs GPT-6 Astra
- GPT-5.5 vs GPT-6 Astra
- Kimi K2.6 vs Kimi K3
- Kimi K2.5 vs Kimi K3
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.