Model comparison
Claude 3 Opus vs GPT-5.2
GPT-5.2 is the stronger model overall, scoring 54.1 to 29.5 on the Noometry Index.
Last verified . 30 shared benchmarks.
Summary
- They share 30 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and GPT-5.2 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.2 leads 60.0 to 14.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 96.1% for GPT-5.2.
Side by side
| Claude 3 Opus | GPT-5.2 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 29.5 | 54.1 |
| Released | 2024-02-29 | 2025-12-11 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $1.75 |
| Output $ / M tokens | — | $14 |
| Results tracked | 46 | 67 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.2 leads
Claude 3 Opus: 32.9 (#267), GPT-5.2: 51.6 (#37)
| Benchmark | Claude 3 Opus | GPT-5.2 |
|---|---|---|
| WeirdML | 19.2% | 72.2% |
| LMArena Coding | 1264 | 1447 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 72.8% |
| LMArena WebDev | — | 1416 |
| SWE-bench Multilingual | — | 66.7% |
| GSO | — | 27.4% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 1,294 |
| AlgoTune | — | 2.05 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use GPT-5.2 leads
Claude 3 Opus: 24.6 (#116), GPT-5.2: 40.2 (#24)
| Benchmark | Claude 3 Opus | GPT-5.2 |
|---|---|---|
| METR Time Horizons | 29.5% | 75.3% |
| Terminal-Bench | — | 64.9% |
| Berkeley Function Calling Leaderboard | — | 55.9% |
| GDPval | — | 49.7% |
| 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 | 10% | — |
| DeepResearch Bench | — | 41.1% |
| LMArena Search | — | 1207 |
| Vending-Bench 2 | — | 3,591 |
Reasoning GPT-5.2 leads
Claude 3 Opus: 14.6 (#324), GPT-5.2: 50.2 (#35)
| Benchmark | Claude 3 Opus | GPT-5.2 |
|---|---|---|
| SimpleBench | 23.5% | 45.8% |
| Chess Puzzles | 5% | 49% |
| EnigmaEval | 0.8% | 10.4% |
| LMArena Hard Prompts | 1245 | 1445 |
| DTBench | 61.6% | 90.9% |
| LMCA | 17% | 43.9% |
| Epoch Capabilities Index | 126.91 | 153.45 |
| ForecastBench | 58.4 | 60.1 |
| ARC-AGI-2 | — | 52.9% |
| Kagi LLM Benchmark | — | 73.3% |
| NYT Connections (extended) | — | 83.6% |
| ARC-AGI-1 | — | 86.2% |
| EBR-Bench | — | 23% |
| LiveBench Reasoning | 40.6% | — |
| Mystery Game Puzzles | — | 23% |
| LiveBench Data Analysis | 57.9% | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math GPT-5.2 leads
Claude 3 Opus: 14.8 (#299), GPT-5.2: 60.0 (#38)
| Benchmark | Claude 3 Opus | GPT-5.2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 96.1% |
| LMArena Math | 1273 | 1440 |
| FrontierMath (Tiers 1-3) | — | 67.4% |
| FrontierMath Tier 4 | — | 31.7% |
| MathArena Final-Answer Competitions | — | 72% |
| ProofBench | — | 15% |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
| FrontierMath (Feb 2025 set) | — | 40.7% |
| FrontierMath Tier 4 (v1) | — | 18.8% |
Knowledge GPT-5.2 leads
Claude 3 Opus: 24.5 (#267), GPT-5.2: 59.3 (#32)
| Benchmark | Claude 3 Opus | GPT-5.2 |
|---|---|---|
| GPQA Diamond | 47.2% | 91.4% |
| SimpleQA Verified | 12.6% | 37.1% |
| LMArena Expert | 1223 | 1445 |
| Humanity's Last Exam | — | 27.8% |
| Confabulations | 22.7% | — |
| Vectara Hallucination Rate | — | 8.4% |
| MMLU | 84.6% | — |
Multimodal GPT-5.2 leads
Claude 3 Opus: 27.1 (#116), GPT-5.2: 51.3 (#7)
| Benchmark | Claude 3 Opus | GPT-5.2 |
|---|---|---|
| LMArena Vision | 1023 | 1268 |
| VPCT | — | 84% |
| Furniture Assembly | — | 38.3% |
| LMArena Document | — | 1405 |
Multilingual GPT-5.2 leads
Claude 3 Opus: 41.4 (#207), GPT-5.2: 53.4 (#67)
| Benchmark | Claude 3 Opus | GPT-5.2 |
|---|---|---|
| LMArena Non-English | 1258 | 1425 |
| LMArena Chinese | 1248 | 1460 |
| LMArena French | 1275 | 1455 |
| LMArena German | 1258 | 1448 |
| LMArena Japanese | 1204 | 1420 |
| LMArena Korean | 1187 | 1392 |
| LMArena Russian | 1280 | 1440 |
| LMArena Spanish | 1246 | 1433 |
Instruction Following GPT-5.2 leads
Claude 3 Opus: 64.1 (#228), GPT-5.2: 74.7 (#89)
| Benchmark | Claude 3 Opus | GPT-5.2 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1417 |
| LiveBench Instruction Following | 63.9% | — |
Long Context GPT-5.2 leads
Claude 3 Opus: 38.2 (#202), GPT-5.2: 44.0 (#78)
| Benchmark | Claude 3 Opus | GPT-5.2 |
|---|---|---|
| LMArena Longer Query | 1259 | 1428 |
| CL-bench | — | 18.2% |
Writing & Preference GPT-5.2 leads
Claude 3 Opus: 47.2 (#213), GPT-5.2: 66.8 (#32)
| Benchmark | Claude 3 Opus | GPT-5.2 |
|---|---|---|
| LMArena Text | 1262 | 1439 |
| LMArena Creative Writing | 1235 | 1401 |
| LMArena Multi-Turn | 1275 | 1458 |
| EQ-Bench Creative Writing | — | 1703 |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than GPT-5.2?
GPT-5.2 is the stronger model overall, scoring 54.1 to 29.5 on the Noometry Index.
Is Claude 3 Opus or GPT-5.2 better for coding?
GPT-5.2 scores higher on coding benchmarks: 51.6 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and GPT-5.2 share?
30 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and GPT-5.2 has 67.