token.app › Compare › Kimi K3 vs Claude Opus 5
Kimi K3 vs Claude Opus 5
Claude Opus 5 leads on 5 of 5 shared benchmarks. Kimi K3 is 1.7× cheaper per token on a blended 3:1 basis. Kimi K3 accepts the larger context window (1.0M).
Head to head
Blended price uses a 3:1 input:output mix
| Kimi K3 | Claude Opus 5 | |
|---|---|---|
| Provider | Moonshot AI | Anthropic |
| Input $/1M | $3.00 | $5.00 |
| Output $/1M | $15.00 | $25.00 |
| Blended $/1M | $6.00 | $10.00 |
| Context window | 1.0M | 1M |
| Max output | — | 128K |
| Released | Jul 2026 | Jul 2026 |
| Licence | Open weights | Proprietary |
| GPQA Diamond | 93.1% | 93.9% |
| FrontierMath T1–3 | 72.2% | 85.6% |
| FrontierMath T4 | 39.0% | 73.2% |
| SimpleQA Verified | 42.7% | 56.7% |
| OTIS Mock AIME | 97.2% | 98.9% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Kimi K3 if…
- Costs less per token — $6.00 vs $10.00 blended
- Larger context window (1.0M)
- Open weights — self-hostable
Choose Claude Opus 5 if…
- Higher GPQA Diamond (93.9% vs 93.1%)
- Higher FrontierMath T1–3 (85.6% vs 72.2%)
- Higher FrontierMath T4 (73.2% vs 39.0%)
- Higher SimpleQA Verified (56.7% vs 42.7%)
- Newer model (released Jul 2026)
FAQ
Which is better, Kimi K3 or Claude Opus 5?
Across the 5 benchmarks both models have independently-run scores for, Kimi K3 leads on 0 and Claude Opus 5 leads on 5. Benchmarks are one input — price and context window are on this page too.
Is Kimi K3 cheaper than Claude Opus 5?
Kimi K3 is cheaper: $6.00 versus $10.00 per million tokens blended at 3:1 input:output. Input alone: $3.00 vs $5.00. Output alone: $15.00 vs $25.00.
What context windows do Kimi K3 and Claude Opus 5 have?
Kimi K3: 1,048,576 tokens. Claude Opus 5: 1,000,000 tokens.
Who makes Kimi K3 and Claude Opus 5?
Kimi K3 is made by Moonshot AI. Claude Opus 5 is made by Anthropic.