token.app › Compare › Grok 4.20 vs Kimi K3
Grok 4.20 vs Kimi K3
Kimi K3 leads on 5 of 5 shared benchmarks. Grok 4.20 is 3.8× cheaper per token on a blended 3:1 basis. Grok 4.20 accepts the larger context window (2M).
Head to head
Blended price uses a 3:1 input:output mix
| Grok 4.20 | Kimi K3 | |
|---|---|---|
| Provider | xAI | Moonshot AI |
| Input $/1M | $1.25 | $3.00 |
| Output $/1M | $2.50 | $15.00 |
| Blended $/1M | $1.56 | $6.00 |
| Context window | 2M | 1.0M |
| Max output | — | — |
| Released | Mar 2026 | Jul 2026 |
| Licence | Proprietary | Open weights |
| GPQA Diamond | 89.3% | 93.1% |
| FrontierMath T1–3 | 44.9% | 72.2% |
| FrontierMath T4 | 17.1% | 39.0% |
| SimpleQA Verified | 35.1% | 42.7% |
| OTIS Mock AIME | 92.2% | 97.2% |
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 Grok 4.20 if…
- Costs less per token — $1.56 vs $6.00 blended
- Larger context window (2M)
Choose Kimi K3 if…
- Higher GPQA Diamond (93.1% vs 89.3%)
- Higher FrontierMath T1–3 (72.2% vs 44.9%)
- Higher FrontierMath T4 (39.0% vs 17.1%)
- Higher SimpleQA Verified (42.7% vs 35.1%)
- Open weights — self-hostable
- Newer model (released Jul 2026)
FAQ
Which is better, Grok 4.20 or Kimi K3?
Across the 5 benchmarks both models have independently-run scores for, Grok 4.20 leads on 0 and Kimi K3 leads on 5. Benchmarks are one input — price and context window are on this page too.
Is Grok 4.20 cheaper than Kimi K3?
Grok 4.20 is cheaper: $1.56 versus $6.00 per million tokens blended at 3:1 input:output. Input alone: $1.25 vs $3.00. Output alone: $2.50 vs $15.00.
What context windows do Grok 4.20 and Kimi K3 have?
Grok 4.20: 2,000,000 tokens. Kimi K3: 1,048,576 tokens.
Who makes Grok 4.20 and Kimi K3?
Grok 4.20 is made by xAI. Kimi K3 is made by Moonshot AI.