Claude 3.7 Sonnet (Reasoning) vs GPT-5.2 (xhigh)
Comparing 2 AI models · 6 benchmarks · Anthropic, OpenAI
Most Affordable
Op
GPT-5.2 (xhigh)
$1.75/1M
Highest Intelligence
Op
GPT-5.2 (xhigh)
90.3% GPQA
Best for Coding
Op
GPT-5.2 (xhigh)
46.7 Coding Index
Price Difference
1.7x
input cost range
Composite Indices
Intelligence, Coding, Math
Standard Benchmarks
Academic and industry benchmarks
Benchmark Winners
6 tests
An
Claude 3.7 Sonnet (Reasoning)
1
- MATH 500
Op
GPT-5.2 (xhigh)
5
- GPQA
- MMLU Pro
- HLE
- LiveCodeBench
- AIME 2025
| Metric | An Claude 3.7 Sonnet (Reasoning) | Op GPT-5.2 (xhigh) |
|---|---|---|
| Pricing Per 1M tokens | ||
| Input Cost | $3.00/1M | $1.75/1M |
| Output Cost | $15.00/1M | $14.00/1M |
| Blended Cost 3:1 input/output ratio | $6.00/1M | $4.81/1M |
| Specifications | ||
| Organization Model creator | Anthropic | OpenAI |
| Release Date Launch date | Feb 24, 2025 | Dec 11, 2025 |
| Performance & Speed | ||
| Throughput Output speed | — | 112.9 tok/s |
| Time to First Token (TTFT) Initial response delay | — | 42184ms |
| Latency Time to first answer token | — | 42184ms |
| Composite Indices | ||
| Intelligence Index Overall reasoning capability | 34.4 | 50.5 |
| Coding Index Programming ability | 26.7 | 46.7 |
| Math Index Mathematical reasoning | 56.3 | 99.0 |
| Standard Benchmarks | ||
| GPQA Graduate-level reasoning | 77.2% | 90.3% |
| MMLU Pro Advanced knowledge | 83.7% | 87.4% |
| HLE Hard language evaluation | 10.3% | 35.4% |
| LiveCodeBench Real-world coding tasks | 47.3% | 88.9% |
| MATH 500 Mathematical problems | 94.7% | — |
| AIME 2025 Advanced math competition | ||