token.app › Compare › Claude Sonnet 5 vs Grok 4.6
Claude Sonnet 5 vs Grok 4.6
Grok 4.6 leads on 4 of 4 shared benchmarks. Grok 4.6 is 1.3× cheaper per token on a blended 3:1 basis. Claude Sonnet 5 accepts the larger context window (1M).
Head to head
Blended price uses a 3:1 input:output mix
| Claude Sonnet 5 | Grok 4.6 | |
|---|---|---|
| Provider | Anthropic | SpaceXAI |
| Input $/1M | $2.00 | $2.00 |
| Output $/1M | $10.00 | $6.00 |
| Blended $/1M | $4.00 | $3.00 |
| Context window | 1M | 500K |
| Max output | 128K | 450K |
| Released | Jun 2026 | Aug 2026 |
| Licence | Proprietary | Proprietary |
| GPQA Diamond | 90.5% | 94.0% |
| FrontierMath T1–3 | 65.6% | 66.0% |
| FrontierMath T4 | 29.3% | 31.7% |
| OTIS Mock AIME | 94.7% | 99.2% |
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 5 if…
- Larger context window (1M)
Choose Grok 4.6 if…
- Costs less per token — $3.00 vs $4.00 blended
- Higher GPQA Diamond (94.0% vs 90.5%)
- Higher FrontierMath T1–3 (66.0% vs 65.6%)
- Higher FrontierMath T4 (31.7% vs 29.3%)
- Higher OTIS Mock AIME (99.2% vs 94.7%)
- Newer model (released Aug 2026)
FAQ
Which is better, Claude Sonnet 5 or Grok 4.6?
Across the 4 benchmarks both models have independently-run scores for, Claude Sonnet 5 leads on 0 and Grok 4.6 leads on 4. Benchmarks are one input — price and context window are on this page too.
Is Claude Sonnet 5 cheaper than Grok 4.6?
Grok 4.6 is cheaper: $3.00 versus $4.00 per million tokens blended at 3:1 input:output. Input alone: $2.00 vs $2.00. Output alone: $10.00 vs $6.00.
What context windows do Claude Sonnet 5 and Grok 4.6 have?
Claude Sonnet 5: 1,000,000 tokens. Grok 4.6: 500,000 tokens.
Who makes Claude Sonnet 5 and Grok 4.6?
Claude Sonnet 5 is made by Anthropic. Grok 4.6 is made by SpaceXAI.