Compare / head-to-head
Claude Sonnet 4.5vsGPT-5.2 Pro
GPT-5.2 Pro leads 7 of 7 shared benchmarks. Claude Sonnet 4.5 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 – 7
GPT-5.2 Pro leads
Cheaper per token
Claude Sonnet 4.5
10.5x cheaper, input + output
Larger context
GPT-5.2 Pro
400K tokens
Provider uptime (30d)
100% · 95.2381%
Anthropic · OpenAI
Claude Sonnet 4.5
Anthropic · released 2025-09-29
textvision
GPT-5.2 Pro
OpenAI · released 2025-12-11
textvision
Quality
Benchmark matrix
7 shared · 13 only Claude Sonnet 4.5 · 3 only GPT-5.2 Pro| Benchmark | Claude Sonnet 4.5 | GPT-5.2 Pro | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 7 | ||||
| GPQA Diamond | 83.4% ↗ | 93.2% ↗ | -9.8 pt | GPT-5.2 Pro |
| AIME 2025 | 84.2% ↗matharena ⚠ | 100% ↗ | -15.8 pt | GPT-5.2 Pro |
| Humanity's Last Exam (no tools) | 17.7% ↗ | 36.6% ↗ | -18.9 pt | GPT-5.2 Pro |
| ARC-AGI-2 (Verified) | 13.6% ↗ | 54.2% ↗ | -40.6 pt | GPT-5.2 Pro |
| FrontierMath Tier 4 v2 (Epoch AI run) | 2.4% ↗epoch | 46% ↗epoch | -43.6 pt | GPT-5.2 Pro |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 23.9% ↗epoch | 74% ↗epoch | -50.1 pt | GPT-5.2 Pro |
| Humanity's Last Exam (with tools) | 33.6% ↗ | 50% ↗ | -16.4 pt | GPT-5.2 Pro |
| Only Claude Sonnet 4.5 reports · 13 | ||||
| SWE-bench Verified | 77.2% ↗ | not reported | — | — |
| GDPval-AA | 1276 ↗ | not reported | — | — |
| MCP Atlas | 43.8% ↗ | not reported | — | — |
| MMMLU | 89.5% ↗ | not reported | — | — |
| MMMU-Pro (no tools) | 63.4% ↗ | not reported | — | — |
| MMMU-Pro (with tools) | 68.9% ↗ | not reported | — | — |
| OSWorld-Verified | 61.4% ↗ | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 77.8% ↗epoch | not reported | — | — |
| SimpleQA Verified | 30.7% ↗epoch | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 71.3% ↗epoch | not reported | — | — |
| Tau2-bench Retail | 86.2% ↗ | not reported | — | — |
| Tau2-bench Telecom | 98% ↗ | not reported | — | — |
| Terminal-Bench 2.0 | 51% ↗ | not reported | — | — |
| Only GPT-5.2 Pro reports · 3 | ||||
| ARC-AGI-1 (Verified) | not reported | 90.5% ↗ | — | — |
| BrowseComp | not reported | 77.9% ↗ | — | — |
| GDPval (wins or ties) | not reported | 74.1% ↗ | — | — |
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 Sonnet 4.5 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 Sonnet 4.5 | GPT-5.2 Pro | Edge |
|---|---|---|---|
| Context window | 200K tokens | 400K tokens | GPT-5.2 Pro |
| Max output | 64K tokens | 128K tokens | GPT-5.2 Pro |
| Input price / 1M | $3 ↗ | $21 ↗ | Claude Sonnet 4.5 |
| Output price / 1M | $15 ↗ | $168 ↗ | Claude Sonnet 4.5 |
| Cached input / 1M | $0.3 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $18 | $189 | Claude Sonnet 4.5 |
| Modalities | text · vision | text · vision | Tie |
| Released | 2025-09-29 | 2025-12-11 | — |
| Cited benchmark scores | 21 | 10 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Claude Sonnet 4.5 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 Sonnet 4.5 and GPT-5.2 Pro on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.