Claude Haiku 4.5 vs Kimi K3
Claude Haiku 4.5 (Anthropic) and Kimi K3 (Moonshot) compared on benchmarks, pricing, context window, and use-case rankings.
- Kimi K3 leads on overall intelligence (ECI 158 vs 142).
- Claude Haiku 4.5 is cheaper on input tokens — $1.00 vs $2.10 per 1M.
- Kimi K3 has a larger context window (1M vs 200K tokens).
- Kimi K3 ranks higher for coding (97th vs 17th percentile).
| Attribute | Claude Haiku 4.5 | Kimi K3 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 142 | 158 |
| Coding | 17 | 97 |
| Math | 7 | 80 |
| Reasoning & Knowledge | 8 | 73 |
| Agentic & Tools | 16 | 80 |
| Specifications | ||
| Developer | Anthropic | Moonshot |
| Family | Claude | Kimi |
| Released | Oct 15, 2025 | Jul 16, 2026 |
| Parameters | — | 2.8T |
| Availability | API access | Open weights (non-commercial) |
| Context window | 200K | 1M |
| Price — $/M input | $1.00 | $2.10 |
| Price — $/M output | $5.00 | $10.95 |
| Inputs | text, image, file | text, image, video |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 67% | 97% |
| APEX | 9% | 39% |
| ARC-AGI | 48% | 95% |
| ARC-AGI-2 | 4% | 60% |
| FrontierMath | 6% | — |
| FrontierMath Tier 4 | 2% | — |
| GPQA Diamond | 71% | 93% |
| MATH Level 5 | 96% | — |
| SimpleQA Verified | 13% | 51% |
| Terminal-Bench | 36% | — |
| WebDev Arena | 1327 | 1674 |
| WeirdML | 45% | 83% |
| Humanity's Last Exam | — | 47% |
| SciCode | — | 60% |
| SimpleBench | — | 61% |
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 Haiku 4.5 better than Kimi K3?
On Epoch AI's Capabilities Index, Kimi K3 scores higher (158) than Claude Haiku 4.5 (142). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is cheaper, Claude Haiku 4.5 or Kimi K3?
Claude Haiku 4.5 is cheaper on input tokens at $1.00 per million, versus $2.10 (representative OpenRouter pricing).
Which has a larger context window, Claude Haiku 4.5 or Kimi K3?
Kimi K3 supports up to 1M tokens, compared with 200K for the other.
Which is better for coding, Claude Haiku 4.5 or Kimi K3?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Kimi K3 ranks higher — 97th vs 17th 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.