DeepSeek V4.1 Flash vs Kimi K3
DeepSeek V4.1 Flash (DeepSeek) and Kimi K3 (Moonshot) compared on benchmarks, pricing, context window, and use-case rankings.
- Kimi K3 leads on overall intelligence (ECI 158 vs 156).
- DeepSeek V4.1 Flash is cheaper on input tokens: $0.04 vs $0.28 per 1M.
- Kimi K3 ranks higher for coding (94th vs 75th percentile).
| Attribute | DeepSeek V4.1 Flash | Kimi K3 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 156 | 158 |
| Coding | 75 | 94 |
| Math | 72 | 64 |
| Reasoning & Knowledge | 60 | 67 |
| Agentic & Tools | 43 | 58 |
| Specifications | ||
| Developer | DeepSeek | Moonshot |
| Family | DeepSeek | Kimi |
| Released | Sep 9, 2026 | Jul 16, 2026 |
| Parameters | 552B | 2.8T |
| Availability | Open weights (unrestricted) | Open weights (non-commercial) |
| Context window | 1M | 1M |
| Price — $/M input | $0.04 | $0.28 |
| Price — $/M output | $0.38 | $9.94 |
| Inputs | text, image | text, image, video |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 98% | 97% |
| APEX | 40% | 48% |
| ARC-AGI | 95% | 95% |
| ARC-AGI-2 | 73% | 60% |
| GPQA Diamond | 90% | 93% |
| Humanity's Last Exam | 39% | 47% |
| SciCode | 52% | 60% |
| SimpleQA Verified | 43% | 51% |
| WebDev Arena | 1614 | 1674 |
| SimpleBench | — | 61% |
| 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
Is DeepSeek V4.1 Flash better than Kimi K3?
On Epoch AI's Capabilities Index, Kimi K3 scores higher (158) than DeepSeek V4.1 Flash (156). The right pick depends on your task, so compare their coding, math, and reasoning scores in the table above.
Which is cheaper, DeepSeek V4.1 Flash or Kimi K3?
DeepSeek V4.1 Flash is cheaper on input tokens at $0.04 per million, versus $0.28 (representative OpenRouter pricing).
Which has a larger context window, DeepSeek V4.1 Flash or Kimi K3?
Neither: both support up to 1M tokens.
Which is better for coding, DeepSeek V4.1 Flash or Kimi K3?
Kimi K3 ranks higher across coding benchmarks like WebDev Arena and SciCode: 94th vs 75th 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.