Model comparison
Claude 3.5 Sonnet vs GPT-5.2 Pro
GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 34.4 on the Noometry Index.
Last verified . 3 shared benchmarks.
Summary
- They share 3 benchmarks with published results for both. Claude 3.5 Sonnet 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 math, where GPT-5.2 Pro leads 64.8 to 18.0.
- The biggest single-benchmark swing is SimpleBench: 41.4% for Claude 3.5 Sonnet and 57.4% for GPT-5.2 Pro.
Side by side
| Claude 3.5 Sonnet | GPT-5.2 Pro | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 34.4 | 52.2 |
| Released | 2024-06-20 | 2025-12-11 |
| Weights | Proprietary | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $21 |
| Output $ / M tokens | — | $168 |
| Results tracked | 60 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude 3.5 Sonnet: 39.5 (#145), GPT-5.2 Pro: —
| Benchmark | Claude 3.5 Sonnet | GPT-5.2 Pro |
|---|---|---|
| Aider Polyglot | 51.6% | — |
| GSO | 4.6% | — |
| WeirdML | 40% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| LMArena Coding | 1343 | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Sonnet: 32.1 (#61), GPT-5.2 Pro: —
| Benchmark | Claude 3.5 Sonnet | GPT-5.2 Pro |
|---|---|---|
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning GPT-5.2 Pro leads
Claude 3.5 Sonnet: 22.5 (#176), GPT-5.2 Pro: 51.8 (#31)
| Benchmark | Claude 3.5 Sonnet | GPT-5.2 Pro |
|---|---|---|
| SimpleBench | 41.4% | 57.4% |
| Epoch Capabilities Index | 133.55 | 155.41 |
| ARC-AGI-2 | — | 54.2% |
| NYT Connections (extended) | — | 79.3% |
| ARC-AGI-1 | — | 90.5% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| LMArena Hard Prompts | 1305 | — |
| DTBench | 67.8% | — |
| LiveBench Data Analysis | 55% | — |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math GPT-5.2 Pro leads
Claude 3.5 Sonnet: 18.0 (#282), GPT-5.2 Pro: 64.8 (#23)
| Benchmark | Claude 3.5 Sonnet | GPT-5.2 Pro |
|---|---|---|
| FrontierMath Tier 4 (v1) | 0% | 31.3% |
| FrontierMath (Tiers 1-3) | — | 74% |
| FrontierMath Tier 4 | — | 46% |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| LMArena Math | 1306 | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
Knowledge Not comparable
Claude 3.5 Sonnet: 28.5 (#236), GPT-5.2 Pro: —
| Benchmark | Claude 3.5 Sonnet | GPT-5.2 Pro |
|---|---|---|
| GPQA Diamond | 55.3% | — |
| Humanity's Last Exam | 4.1% | — |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| GPQA (HELM) | 56.5% | — |
| LMArena Expert | 1264 | — |
| MMLU | 87.3% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.0 (#115), GPT-5.2 Pro: —
| Benchmark | Claude 3.5 Sonnet | GPT-5.2 Pro |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual Not comparable
Claude 3.5 Sonnet: 43.4 (#180), GPT-5.2 Pro: —
| Benchmark | Claude 3.5 Sonnet | GPT-5.2 Pro |
|---|---|---|
| LMArena Non-English | 1283 | — |
| LMArena Chinese | 1271 | — |
| LMArena French | 1304 | — |
| LMArena German | 1297 | — |
| LMArena Japanese | 1234 | — |
| LMArena Korean | 1200 | — |
| LMArena Russian | 1305 | — |
| LMArena Spanish | 1289 | — |
Instruction Following Not comparable
Claude 3.5 Sonnet: 69.0 (#177), GPT-5.2 Pro: —
| Benchmark | Claude 3.5 Sonnet | GPT-5.2 Pro |
|---|---|---|
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
| LMArena Instruction Following | 1297 | — |
Long Context Not comparable
Claude 3.5 Sonnet: 39.9 (#162), GPT-5.2 Pro: —
| Benchmark | Claude 3.5 Sonnet | GPT-5.2 Pro |
|---|---|---|
| LMArena Longer Query | 1311 | — |
Writing & Preference Not comparable
Claude 3.5 Sonnet: 53.0 (#159), GPT-5.2 Pro: —
| Benchmark | Claude 3.5 Sonnet | GPT-5.2 Pro |
|---|---|---|
| LMArena Text | 1298 | — |
| LMArena Creative Writing | 1292 | — |
| Short-Story Creative Writing | 80.3% | — |
| EQ-Bench Creative Writing | 1451 | — |
| WildBench | 79.2% | — |
| LMArena Multi-Turn | 1326 | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than GPT-5.2 Pro?
GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 34.4 on the Noometry Index.
How many benchmarks do Claude 3.5 Sonnet and GPT-5.2 Pro share?
3 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and GPT-5.2 Pro has 8.