token.app โ€บ Compare โ€บ Claude Sonnet 4 vs Kimi K3

Claude Sonnet 4 vs Kimi K3

Kimi K3 leads on 2 of 2 shared benchmarks. Kimi K3 accepts the larger context window (1.0M).

Head to head
Blended price uses a 3:1 input:output mix
Claude Sonnet 4Kimi K3
ProviderAnthropicMoonshot AI
Input $/1M$3.00$3.00
Output $/1M$15.00$15.00
Blended $/1M$6.00$6.00
Context window1M1.0M
Max output64Kโ€”
ReleasedMay 2025Jul 2026
LicenceProprietaryOpen weights
GPQA Diamond 79.2% 93.1%
OTIS Mock AIME 71.1% 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 Claude Sonnet 4 ifโ€ฆ
  • No clear advantage on the data we hold.
Choose Kimi K3 ifโ€ฆ
  • Higher GPQA Diamond (93.1% vs 79.2%)
  • Higher OTIS Mock AIME (97.2% vs 71.1%)
  • Larger context window (1.0M)
  • Open weights โ€” self-hostable
  • Newer model (released Jul 2026)
FAQ
Which is better, Claude Sonnet 4 or Kimi K3?
Across the 2 benchmarks both models have independently-run scores for, Claude Sonnet 4 leads on 0 and Kimi K3 leads on 2. Benchmarks are one input โ€” price and context window are on this page too.
Is Claude Sonnet 4 cheaper than Kimi K3?
They cost the same on a blended 3:1 basis: $6.00 per million tokens.
What context windows do Claude Sonnet 4 and Kimi K3 have?
Claude Sonnet 4: 1,000,000 tokens. Kimi K3: 1,048,576 tokens.
Who makes Claude Sonnet 4 and Kimi K3?
Claude Sonnet 4 is made by Anthropic. Kimi K3 is made by Moonshot AI.
Related comparisons