Model comparison
Claude Opus 4.1 vs GPT-5.2
GPT-5.2 is the stronger model overall, scoring 54.1 to 41.0 on the Noometry Index.
Last verified . 45 shared benchmarks.
Summary
- They share 45 benchmarks with published results for both. Claude Opus 4.1 scores higher in 2 categories and GPT-5.2 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.2 leads 60.0 to 22.3.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 12.6% for Claude Opus 4.1 and 67.4% for GPT-5.2.
- GPT-5.2 is cheaper at $1.75 / $14 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- GPT-5.2 accepts more context: 400K tokens versus 200K.
Side by side
| Claude Opus 4.1 | GPT-5.2 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 41.0 | 54.1 |
| Released | 2025-08-05 | 2025-12-11 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 400K |
| Max output | 32K | 128K |
| Input $ / M tokens | $15 | $1.75 |
| Output $ / M tokens | $75 | $14 |
| Results tracked | 48 | 67 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.2 leads
Claude Opus 4.1: 44.4 (#73), GPT-5.2: 51.6 (#37)
| Benchmark | Claude Opus 4.1 | GPT-5.2 |
|---|---|---|
| SWE-bench Verified | 73.3% | 73.8% |
| LMArena WebDev | 1390 | 1416 |
| WeirdML | 45.9% | 72.2% |
| LMArena Coding | 1479 | 1447 |
| ALE-Bench | 674.77 | 1,294 |
| AlgoTune | 1.34 | 2.05 |
| SWE-bench Verified (bash only) | — | 72.8% |
| SWE-bench Multilingual | — | 66.7% |
| GSO | — | 27.4% |
Agentic & Tool Use GPT-5.2 leads
Claude Opus 4.1: 35.0 (#41), GPT-5.2: 40.2 (#24)
| Benchmark | Claude Opus 4.1 | GPT-5.2 |
|---|---|---|
| Terminal-Bench | 38% | 64.9% |
| GDPval | 43.6% | 49.7% |
| DeepResearch Bench | 48.3% | 41.1% |
| LMArena Search | 1148 | 1207 |
| METR Time Horizons | 66.8% | 75.3% |
| Berkeley Function Calling Leaderboard | — | 55.9% |
| Remote Labor Index | — | 2.5% |
| τ²-bench Airline | — | 83% |
| τ²-bench Banking | — | 32.2% |
| τ²-bench Retail | — | 81.6% |
| τ²-bench Telecom | — | 89.7% |
| Cybench | 42% | — |
| Vending-Bench 2 | — | 3,591 |
Reasoning GPT-5.2 leads
Claude Opus 4.1: 32.2 (#76), GPT-5.2: 50.2 (#35)
| Benchmark | Claude Opus 4.1 | GPT-5.2 |
|---|---|---|
| SimpleBench | 60% | 45.8% |
| Chess Puzzles | 7% | 49% |
| EnigmaEval | 7.2% | 10.4% |
| EBR-Bench | 7.9% | 23% |
| LMArena Hard Prompts | 1443 | 1445 |
| Mystery Game Puzzles | 21% | 23% |
| DTBench | 80% | 90.9% |
| LMCA | 37.1% | 43.9% |
| Epoch Capabilities Index | 144.12 | 153.45 |
| ForecastBench | 62 | 60.1 |
| ARC-AGI-2 | — | 52.9% |
| Kagi LLM Benchmark | — | 73.3% |
| NYT Connections (extended) | — | 83.6% |
| ARC-AGI-1 | — | 86.2% |
Math GPT-5.2 leads
Claude Opus 4.1: 22.3 (#277), GPT-5.2: 60.0 (#38)
| Benchmark | Claude Opus 4.1 | GPT-5.2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 12.6% | 67.4% |
| FrontierMath Tier 4 | 2.4% | 31.7% |
| OTIS Mock AIME 2024-2025 | 68.9% | 96.1% |
| LMArena Math | 1431 | 1440 |
| FrontierMath (Feb 2025 set) | 7.2% | 40.7% |
| FrontierMath Tier 4 (v1) | 4.2% | 18.8% |
| MathArena Final-Answer Competitions | — | 72% |
| ProofBench | — | 15% |
Knowledge GPT-5.2 leads
Claude Opus 4.1: 42.0 (#101), GPT-5.2: 59.3 (#32)
| Benchmark | Claude Opus 4.1 | GPT-5.2 |
|---|---|---|
| GPQA Diamond | 77.3% | 91.4% |
| Humanity's Last Exam | 11.5% | 27.8% |
| Vectara Hallucination Rate | 11.8% | 8.4% |
| LMArena Expert | 1439 | 1445 |
| SimpleQA Verified | — | 37.1% |
| Confabulations | 17.1% | — |
Multimodal GPT-5.2 leads
Claude Opus 4.1: 26.8 (#119), GPT-5.2: 51.3 (#7)
| Benchmark | Claude Opus 4.1 | GPT-5.2 |
|---|---|---|
| VPCT | 35% | 84% |
| LMArena Vision | — | 1268 |
| Furniture Assembly | — | 38.3% |
| LMArena Document | — | 1405 |
Multilingual GPT-5.2 leads
Claude Opus 4.1: 52.0 (#95), GPT-5.2: 53.4 (#67)
| Benchmark | Claude Opus 4.1 | GPT-5.2 |
|---|---|---|
| LMArena Non-English | 1405 | 1425 |
| LMArena Chinese | 1427 | 1460 |
| LMArena French | 1431 | 1455 |
| LMArena German | 1413 | 1448 |
| LMArena Japanese | 1378 | 1420 |
| LMArena Korean | 1380 | 1392 |
| LMArena Russian | 1422 | 1440 |
| LMArena Spanish | 1448 | 1433 |
Instruction Following Too close to call
Claude Opus 4.1: 75.6 (#58), GPT-5.2: 74.7 (#89)
| Benchmark | Claude Opus 4.1 | GPT-5.2 |
|---|---|---|
| LMArena Instruction Following | 1435 | 1417 |
Long Context Too close to call
Claude Opus 4.1: 44.5 (#63), GPT-5.2: 44.0 (#78)
| Benchmark | Claude Opus 4.1 | GPT-5.2 |
|---|---|---|
| LMArena Longer Query | 1455 | 1428 |
| CL-bench | — | 18.2% |
Writing & Preference GPT-5.2 leads
Claude Opus 4.1: 62.4 (#74), GPT-5.2: 66.8 (#32)
| Benchmark | Claude Opus 4.1 | GPT-5.2 |
|---|---|---|
| LMArena Text | 1419 | 1439 |
| LMArena Creative Writing | 1412 | 1401 |
| LMArena Multi-Turn | 1444 | 1458 |
| Short-Story Creative Writing | 84.7% | — |
| EQ-Bench Creative Writing | — | 1703 |
Frequently asked questions
Is Claude Opus 4.1 better than GPT-5.2?
GPT-5.2 is the stronger model overall, scoring 54.1 to 41.0 on the Noometry Index.
Which is cheaper, Claude Opus 4.1 or GPT-5.2?
GPT-5.2 is cheaper. It lists at $1.75 per million input tokens and $14 per million output tokens; Claude Opus 4.1 lists at $15 and $75.
Is Claude Opus 4.1 or GPT-5.2 better for coding?
GPT-5.2 scores higher on coding benchmarks: 51.6 versus 44.4 in the Noometry coding category.
Which has the bigger context window?
GPT-5.2 does, with 400K tokens against 200K.
How many benchmarks do Claude Opus 4.1 and GPT-5.2 share?
45 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and GPT-5.2 has 67.