Model comparison
Claude Opus 4 vs GPT-5.2 Pro
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 43.1 on the Noometry Index. Claude Opus 4 costs 1.9× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
Summary
- They share 5 benchmarks with published results for both. Claude Opus 4 scores higher in 0 categories and GPT-5.2 Pro in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.2 Pro leads 51.5 to 27.3.
- The biggest single-benchmark swing is ARC-AGI-1: 35.7% for Claude Opus 4 and 90.5% for GPT-5.2 Pro.
- Claude Opus 4 is cheaper at $15 / $75 per million input/output tokens, against $21 / $168 for GPT-5.2 Pro.
- GPT-5.2 Pro accepts more context: 400K tokens versus 200K.
Side by side
| Claude Opus 4 | GPT-5.2 Pro | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 43.1 | 52.3 |
| Released | 2025-05-22 | 2025-12-11 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 400K |
| Max output | 32K | 128K |
| Input $ / M tokens | $15 | $21 |
| Output $ / M tokens | $75 | $168 |
| Results tracked | 56 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude Opus 4: 47.2 (#62), GPT-5.2 Pro: —
| Benchmark | Claude Opus 4 | GPT-5.2 Pro |
|---|---|---|
| SWE-bench Verified | 70.7% | — |
| SWE-bench Verified (bash only) | 67.6% | — |
| Aider Polyglot | 72% | — |
| GSO | 6.9% | — |
| WeirdML | 43.7% | — |
| LMArena Coding | 1442 | — |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Not comparable
Claude Opus 4: 34.8 (#42), GPT-5.2 Pro: —
| Benchmark | Claude Opus 4 | GPT-5.2 Pro |
|---|---|---|
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
Reasoning GPT-5.2 Pro leads
Claude Opus 4: 27.3 (#121), GPT-5.2 Pro: 51.5 (#33)
| Benchmark | Claude Opus 4 | GPT-5.2 Pro |
|---|---|---|
| ARC-AGI-2 | 8.6% | 54.2% |
| SimpleBench | 58.8% | 57.4% |
| ARC-AGI-1 | 35.7% | 90.5% |
| Epoch Capabilities Index | 142.67 | 155.4 |
| Kagi LLM Benchmark | 74.3% | — |
| NYT Connections (extended) | — | 79.3% |
| CritPt | 0.3% | — |
| EnigmaEval | 5.6% | — |
| LMArena Hard Prompts | 1399 | — |
| DTBench | 81.6% | — |
| LMCA | 37.4% | — |
| ForecastBench | 61.1 | — |
Math GPT-5.2 Pro leads
Claude Opus 4: 42.0 (#86), GPT-5.2 Pro: 65.3 (#29)
| Benchmark | Claude Opus 4 | GPT-5.2 Pro |
|---|---|---|
| FrontierMath Tier 4 (v1) | 4.2% | 31.3% |
| FrontierMath (Tiers 1-3) | — | 74% |
| FrontierMath Tier 4 | — | 46% |
| OTIS Mock AIME 2024-2025 | 64.4% | — |
| Omni-MATH | 61.6% | — |
| LMArena Math | 1390 | — |
| MATH Level 5 | 85% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |
Knowledge Not comparable
Claude Opus 4: 44.0 (#88), GPT-5.2 Pro: —
| Benchmark | Claude Opus 4 | GPT-5.2 Pro |
|---|---|---|
| GPQA Diamond | 76.3% | — |
| Humanity's Last Exam | 10.7% | — |
| MMLU-Pro | 87.5% | — |
| Confabulations | 15.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 70.8% | — |
| LMArena Expert | 1386 | — |
Multimodal Not comparable
Claude Opus 4: 31.5 (#106), GPT-5.2 Pro: —
| Benchmark | Claude Opus 4 | GPT-5.2 Pro |
|---|---|---|
| LMArena Vision | 1192 | — |
| GeoBench | 49% | — |
| VPCT | 38% | — |
Multilingual Not comparable
Claude Opus 4: 48.8 (#138), GPT-5.2 Pro: —
| Benchmark | Claude Opus 4 | GPT-5.2 Pro |
|---|---|---|
| LMArena Non-English | 1362 | — |
| LMArena Chinese | 1386 | — |
| LMArena French | 1372 | — |
| LMArena German | 1391 | — |
| LMArena Japanese | 1331 | — |
| LMArena Korean | 1321 | — |
| LMArena Russian | 1392 | — |
| LMArena Spanish | 1389 | — |
Instruction Following Not comparable
Claude Opus 4: 77.1 (#28), GPT-5.2 Pro: —
| Benchmark | Claude Opus 4 | GPT-5.2 Pro |
|---|---|---|
| IFEval | 91.8% | — |
| LMArena Instruction Following | 1406 | — |
Long Context Not comparable
Claude Opus 4: 39.6 (#172), GPT-5.2 Pro: —
| Benchmark | Claude Opus 4 | GPT-5.2 Pro |
|---|---|---|
| Fiction.LiveBench | 61.1% | — |
| LMArena Longer Query | 1422 | — |
Writing & Preference Not comparable
Claude Opus 4: 61.2 (#89), GPT-5.2 Pro: —
| Benchmark | Claude Opus 4 | GPT-5.2 Pro |
|---|---|---|
| LMArena Text | 1377 | — |
| LMArena Creative Writing | 1387 | — |
| Short-Story Creative Writing | 83.6% | — |
| EQ-Bench Creative Writing | 1580 | — |
| WildBench | 85.2% | — |
| LMArena Multi-Turn | 1396 | — |
Frequently asked questions
Is Claude Opus 4 better than GPT-5.2 Pro?
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 43.1 on the Noometry Index. Claude Opus 4 costs 1.9× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4 or GPT-5.2 Pro?
Claude Opus 4 is cheaper. It lists at $15 per million input tokens and $75 per million output tokens; GPT-5.2 Pro lists at $21 and $168.
Which has the bigger context window?
GPT-5.2 Pro does, with 400K tokens against 200K.
How many benchmarks do Claude Opus 4 and GPT-5.2 Pro share?
5 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and GPT-5.2 Pro has 8.