DeepSeek V4 Flash 0731 vs Kimi K3
DeepSeek V4 Flash 0731 (DeepSeek) and Kimi K3 (Moonshot) compared on benchmarks, pricing, context window, and use-case rankings.
- Kimi K3 leads on overall intelligence (ECI 157 vs 154).
- DeepSeek V4 Flash 0731 is cheaper on input tokens — $0.08 vs $2.80 per 1M.
- DeepSeek V4 Flash 0731 has a larger context window (1.3M vs 1M tokens).
- Kimi K3 ranks higher for coding (99th vs 79th percentile).
| Attribute | DeepSeek V4 Flash 0731 | Kimi K3 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 154 | 157 |
| Coding | 79 | 99 |
| Math | 68 | 82 |
| Reasoning & Knowledge | 63 | 78 |
| Agentic & Tools | — | 84 |
| Specifications | ||
| Developer | DeepSeek | Moonshot |
| Family | DeepSeek | Kimi |
| Released | Jul 31, 2026 | Jul 16, 2026 |
| Parameters | — | 2.8T |
| Availability | Open weights (unrestricted) | Open weights (non-commercial) |
| Context window | 1.3M | 1M |
| Price — $/M input | $0.08 | $2.80 |
| Price — $/M output | $0.18 | $14.00 |
| Inputs | text | text, image, video |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 94% | 97% |
| ARC-AGI | 89% | 95% |
| ARC-AGI-2 | 61% | 60% |
| GPQA Diamond | 91% | 93% |
| Humanity's Last Exam | 39% | 47% |
| SciCode | 50% | 59% |
| SimpleQA Verified | 35% | 43% |
| WebDev Arena | 1577 | 1682 |
| WeirdML | 63% | 83% |
| APEX | — | 39% |
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 Flash 0731 better than Kimi K3?
On Epoch AI's Capabilities Index, Kimi K3 scores higher (157) than DeepSeek V4 Flash 0731 (154). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is cheaper, DeepSeek V4 Flash 0731 or Kimi K3?
DeepSeek V4 Flash 0731 is cheaper on input tokens at $0.08 per million, versus $2.80 (representative OpenRouter pricing).
Which has a larger context window, DeepSeek V4 Flash 0731 or Kimi K3?
DeepSeek V4 Flash 0731 supports up to 1.3M tokens, compared with 1M for the other.
Which is better for coding, DeepSeek V4 Flash 0731 or Kimi K3?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Kimi K3 ranks higher — 99th vs 79th 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.