▸ compare
Anthropic: Claude Sonnet 4.5 vs Google: Gemini 2.5 Pro
Side-by-side benchmark comparison based on independent public data. Scores, pricing, context, and task breakdown.
▸ verdict
Anthropic: Claude Sonnet 4.5
85.7
higher score
vs
Google: Gemini 2.5 Pro
81.2
Anthropic: Claude Sonnet 4.5 leads with a higher composite benchmark score. It's the stronger choice for general-purpose tasks based on public benchmark data.
▸ score breakdown
| Task | Anthropic: Claude Sonnet 4.5 | Google: Gemini 2.5 Pro | Δ |
|---|---|---|---|
| Overall | 85.7 | 81.2 | +4.5 |
| Coding | 59.8 | 50.7 | +9.1 |
| Reasoning | 45.3 | 49.1 | -3.8 |
| Math | — | — | — |
| Writing | 84.3 | 72.6 | +11.7 |
| JSON | 28.6 | — | — |
▸ specs & pricing
| Attribute | Anthropic: Claude Sonnet 4.5 | Google: Gemini 2.5 Pro |
|---|---|---|
| Provider | Anthropic | |
| Context window | 1M | 1M |
| Input $/M tokens | $3.00/M | $1.25/M |
| Output $/M tokens | $15.00/M | $10.00/M |
| Weights | proprietary | proprietary |
▸ frequently asked
Is Anthropic: Claude Sonnet 4.5 better than Google: Gemini 2.5 Pro?
Anthropic: Claude Sonnet 4.5 scores higher overall (85.7 vs 81.2) in the benchmark composite. The best choice depends on the specific use case and budget.
Which is cheaper: Anthropic: Claude Sonnet 4.5 or Google: Gemini 2.5 Pro?
Google: Gemini 2.5 Pro is cheaper at $1.25/M input tokens vs $3/M for Anthropic: Claude Sonnet 4.5.
Which model is better for coding?
Anthropic: Claude Sonnet 4.5 leads on coding with a score of 59.8 vs 50.7 for Google: Gemini 2.5 Pro. This is based on SWE-Bench, Aider Polyglot, and LiveCodeBench data.