Compare / head-to-head
Claude 3.7 SonnetvsGPT-5.2 Pro
GPT-5.2 Pro leads 2 of 2 shared benchmarks. Claude 3.7 Sonnet is 10.5x cheaper per token. GPT-5.2 Pro has the larger context window (400K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 2
GPT-5.2 Pro leads
Cheaper per token
Claude 3.7 Sonnet
10.5x cheaper, input + output
Larger context
GPT-5.2 Pro
400K tokens
Provider uptime (30d)
100% · 94.2446%
Anthropic · OpenAI
Claude 3.7 Sonnet
Anthropic · released 2025-02-24
textvision
GPT-5.2 Pro
OpenAI · released 2025-12-11
textvision
Quality
Benchmark matrix
2 shared · 3 only Claude 3.7 Sonnet · 8 only GPT-5.2 Pro| Benchmark | Claude 3.7 Sonnet | GPT-5.2 Pro | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| GPQA Diamond | 79.7% ↗epoch | 93.2% ↗ | -13.5 pt | GPT-5.2 Pro |
| AIME 2025 | 49.2% ↗matharena ⚠ | 100% ↗ | -50.8 pt | GPT-5.2 Pro |
| Only Claude 3.7 Sonnet reports · 3 | ||||
| SWE-bench Verified | 70.3% ↗ | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 57.8% ↗epoch | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 61% ↗epoch | not reported | — | — |
| Only GPT-5.2 Pro reports · 8 | ||||
| Humanity's Last Exam (no tools) | not reported | 36.6% ↗ | — | — |
| ARC-AGI-1 (Verified) | not reported | 90.5% ↗ | — | — |
| ARC-AGI-2 (Verified) | not reported | 54.2% ↗ | — | — |
| BrowseComp | not reported | 77.9% ↗ | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | not reported | 46% ↗epoch | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | not reported | 74% ↗epoch | — | — |
| GDPval (wins or ties) | not reported | 74.1% ↗ | — | — |
| Humanity's Last Exam (with tools) | not reported | 50% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Claude 3.7 Sonnet minus GPT-5.2 Pro in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Claude 3.7 Sonnet | GPT-5.2 Pro | Edge |
|---|---|---|---|
| Context window | 200K tokens | 400K tokens | GPT-5.2 Pro |
| Max output | 128K tokens | 128K tokens | Tie |
| Input price / 1M | $3 ↗ | $21 ↗ | Claude 3.7 Sonnet |
| Output price / 1M | $15 ↗ | $168 ↗ | Claude 3.7 Sonnet |
| Cached input / 1M | $0.3 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $18 | $189 | Claude 3.7 Sonnet |
| Modalities | text · vision | text · vision | Tie |
| Released | 2025-02-24 | 2025-12-11 | — |
| Cited benchmark scores | 5 | 10 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Claude 3.7 Sonnet vs …
Models sharing the most benchmarksMore matchups
GPT-5.2 Pro vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude 3.7 Sonnet and GPT-5.2 Pro on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.