Claude Sonnet 5 vs Kimi K3
Claude Sonnet 5 (Anthropic) and Kimi K3 (Moonshot) compared on benchmarks, pricing, context window, and use-case rankings.
- Kimi K3 leads on overall intelligence (ECI 157 vs 156).
- Claude Sonnet 5 is cheaper on input tokens — $2.00 vs $2.80 per 1M.
- Kimi K3 has a larger context window (1M vs 1M tokens).
- Kimi K3 ranks higher for coding (99th vs 79th percentile).
| Attribute | Claude Sonnet 5 | Kimi K3 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 156 | 157 |
| Coding | 79 | 99 |
| Math | 70 | 82 |
| Reasoning & Knowledge | 60 | 78 |
| Agentic & Tools | 64 | 84 |
| Specifications | ||
| Developer | Anthropic | Moonshot |
| Family | Claude | Kimi |
| Released | Jun 30, 2026 | Jul 16, 2026 |
| Parameters | — | 2.8T |
| Availability | API access | Open weights (non-commercial) |
| Context window | 1M | 1M |
| Price — $/M input | $2.00 | $2.80 |
| Price — $/M output | $10.00 | $14.00 |
| Inputs | text, image, file | text, image, video |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 95% | 97% |
| APEX | 33% | 39% |
| GPQA Diamond | 91% | 93% |
| GSO (code optimization) | 37% | — |
| Humanity's Last Exam | 41% | 47% |
| SciCode | 54% | 59% |
| SimpleBench | 61% | — |
| SimpleQA Verified | 25% | 43% |
| WebDev Arena | 1544 | 1682 |
| WeirdML | 69% | 83% |
| ARC-AGI | — | 95% |
| ARC-AGI-2 | — | 60% |
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 Claude Sonnet 5 better than Kimi K3?
On Epoch AI's Capabilities Index, Kimi K3 scores higher (157) than Claude Sonnet 5 (156). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is cheaper, Claude Sonnet 5 or Kimi K3?
Claude Sonnet 5 is cheaper on input tokens at $2.00 per million, versus $2.80 (representative OpenRouter pricing).
Which has a larger context window, Claude Sonnet 5 or Kimi K3?
Kimi K3 supports up to 1M tokens, compared with 1M for the other.
Which is better for coding, Claude Sonnet 5 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.