Kimi K3 vs Qwen 3.7 Max
Kimi K3 (Moonshot) and Qwen 3.7 Max (Alibaba) compared on benchmarks, pricing, context window, and use-case rankings.
- Kimi K3 leads on overall intelligence (ECI 158 vs 154).
- Qwen 3.7 Max is cheaper on input tokens — $1.48 vs $2.55 per 1M.
- Kimi K3 has a larger context window (1M vs 1M tokens).
- Kimi K3 ranks higher for coding (97th vs 68th percentile).
| Attribute | Kimi K3 | Qwen 3.7 Max |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 158 | 154 |
| Coding | 97 | 68 |
| Math | 81 | 71 |
| Reasoning & Knowledge | 73 | 76 |
| Agentic & Tools | 80 | 80 |
| Specifications | ||
| Developer | Moonshot | Alibaba |
| Family | Kimi | Qwen |
| Released | Jul 16, 2026 | May 19, 2026 |
| Parameters | 2.8T | — |
| Availability | Open weights (non-commercial) | — |
| Context window | 1M | 1M |
| Price — $/M input | $2.55 | $1.48 |
| Price — $/M output | $12.75 | $4.42 |
| Inputs | text, image, video | text |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 97% | 96% |
| APEX | 39% | — |
| ARC-AGI | 95% | — |
| ARC-AGI-2 | 60% | — |
| GPQA Diamond | 93% | 91% |
| Humanity's Last Exam | 47% | 41% |
| SciCode | 60% | 50% |
| SimpleBench | 61% | 70% |
| SimpleQA Verified | 51% | 56% |
| WebDev Arena | 1674 | 1517 |
| WeirdML | 83% | — |
| SWE-bench Verified | — | 77% |
| τ²-bench | — | 95% |
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
Is Kimi K3 better than Qwen 3.7 Max?
On Epoch AI's Capabilities Index, Kimi K3 scores higher (158) than Qwen 3.7 Max (154). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is cheaper, Kimi K3 or Qwen 3.7 Max?
Qwen 3.7 Max is cheaper on input tokens at $1.48 per million, versus $2.55 (representative OpenRouter pricing).
Which has a larger context window, Kimi K3 or Qwen 3.7 Max?
Kimi K3 supports up to 1M tokens, compared with 1M for the other.
Which is better for coding, Kimi K3 or Qwen 3.7 Max?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Kimi K3 ranks higher — 97th vs 68th 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.