Claude Sonnet 4.6 vs Gemini 2.5 Pro
Claude Sonnet 4.6 edges ahead on overall intelligence (RunFree 66.2 vs 22.3). Here's how they stack up on benchmarks, price and specs.
Claude Sonnet 4.6
Anthropic
Gemini 2.5 Pro
Google
Shared benchmarks (4)
Loading chart…
| Claude Sonnet 4.6 | Gemini 2.5 Pro | |
|---|---|---|
| RunFree Score | 66.2 | 22.3 |
| Blended price / 1M | $6.00 | $3.44 |
| Input / 1M | $3.00 | $1.25 |
| Output / 1M | $15.00 | $10.00 |
| Context window | 1M | 1.0M |
| Max output | 128K | 66K |
| Reasoning model | Yes | Yes |
| AIME 2025 | 95.6% | 88% |
| GPQA Diamond | 89.9% | 86.4% |
| Humanity's Last Exam | 33.2% | 21.6% |
| SWE-Bench Verified | 79.6% | 59.6% |
| Wins | 6 | 4 |
A blank means the metric is tied or one model has no verified data. Prices are blended 3:1 input:output.
Compare more: Claude Sonnet 4.6 card · Gemini 2.5 Pro card · full leaderboard