Kimi K3 vs Qwen3.7-Max
Kimi K3 (Moonshot) and Qwen3.7-Max (Alibaba) compared on benchmarks, pricing, context window, and use-case rankings.
- Kimi K3 leads on overall intelligence (ECI 158 vs 154).
- Qwen3.7-Max is cheaper on input tokens: $1.48 vs $1.85 per 1M.
- Kimi K3 ranks higher for coding (94th vs 62nd percentile).
| Attribute | Kimi K3 | Qwen3.7-Max |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 158 | 154 |
| Coding | 94 | 62 |
| Math | 64 | 55 |
| Reasoning & Knowledge | 67 | 71 |
| Agentic & Tools | 58 | 77 |
| Specifications | ||
| Developer | Moonshot | Alibaba |
| Family | Kimi | Qwen |
| Released | Jul 16, 2026 | May 19, 2026 |
| Parameters | 2.8T | — |
| Availability | Open weights (non-commercial) | API access |
| Context window | 1M | 1M |
| Price — $/M input | $1.85 | $1.48 |
| Price — $/M output | $9.50 | $4.42 |
| Inputs | text, image, video | text |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 97% | 96% |
| APEX | 48% | — |
| 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 Qwen3.7-Max?
On Epoch AI's Capabilities Index, Kimi K3 scores higher (158) than Qwen3.7-Max (154). The right pick depends on your task, so compare their coding, math, and reasoning scores in the table above.
Which is cheaper, Kimi K3 or Qwen3.7-Max?
Qwen3.7-Max is cheaper on input tokens at $1.48 per million, versus $1.85 (representative OpenRouter pricing).
Which has a larger context window, Kimi K3 or Qwen3.7-Max?
Neither: both support up to 1M tokens.
Which is better for coding, Kimi K3 or Qwen3.7-Max?
Kimi K3 ranks higher across coding benchmarks like WebDev Arena and SciCode: 94th vs 62nd 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.