Model comparison
Claude Sonnet 5 vs GPT-5.2
Claude Sonnet 5 and GPT-5.2 score almost the same on the Noometry Index (54.5 vs 54.1), so choose on price, context window or the category you care about most.
Last verified . 40 shared benchmarks.
Summary
- They share 40 benchmarks with published results for both. Claude Sonnet 5 scores higher in 7 categories and GPT-5.2 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where GPT-5.2 leads 50.9 to 42.4.
- The biggest single-benchmark swing is ProofBench: 77% for Claude Sonnet 5 and 15% for GPT-5.2.
- Claude Sonnet 5 is cheaper at $2 / $10 per million input/output tokens, against $1.75 / $14 for GPT-5.2.
- Claude Sonnet 5 accepts more context: 1M tokens versus 400K.
Side by side
| Claude Sonnet 5 | GPT-5.2 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 54.5 | 54.1 |
| Released | 2026-06-29 | 2025-12-11 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 400K |
| Max output | 128K | 128K |
| Input $ / M tokens | $2 | $1.75 |
| Output $ / M tokens | $10 | $14 |
| Results tracked | 51 | 67 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#20), GPT-5.2: 52.2 (#32)
| Benchmark | Claude Sonnet 5 | GPT-5.2 |
|---|---|---|
| LMArena WebDev | 1540 | 1415 |
| GSO | 37.3% | 27.4% |
| WeirdML | 68.8% | 72.2% |
| LMArena Coding | 1483 | 1447 |
| ALE-Bench | 1,463 | 1,294 |
| SWE-bench Verified | — | 73.8% |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| SWE-bench Verified (bash only) | — | 72.8% |
| CursorBench | 34.1% | — |
| SWE-bench Multilingual | — | 66.7% |
| SciCode | 53.6% | — |
| AlgoTune | — | 2.05 |
Agentic & Tool Use Claude Sonnet 5 leads
Claude Sonnet 5: 42.7 (#16), GPT-5.2: 40.0 (#24)
| Benchmark | Claude Sonnet 5 | GPT-5.2 |
|---|---|---|
| LMArena Search | 1194 | 1207 |
| Vending-Bench 2 | 6,378 | 3,591 |
| Terminal-Bench | — | 64.9% |
| APEX-Agents | 54.5% | — |
| 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% |
| DeepResearch Bench | — | 41.1% |
| GBAEval | 65.3% | — |
| METR Time Horizons | — | 75.3% |
Reasoning GPT-5.2 leads
Claude Sonnet 5: 48.2 (#37), GPT-5.2: 50.1 (#33)
| Benchmark | Claude Sonnet 5 | GPT-5.2 |
|---|---|---|
| SimpleBench | 60.6% | 45.8% |
| NYT Connections (extended) | 75.1% | 83.6% |
| Chess Puzzles | 35% | 49% |
| LMArena Hard Prompts | 1461 | 1445 |
| Mystery Game Puzzles | 35% | 23% |
| DTBench | 92.5% | 90.9% |
| LMCA | 50% | 43.9% |
| Epoch Capabilities Index | 156.34 | 153.45 |
| ForecastBench | 61.1 | 60.1 |
| ARC-AGI-2 | — | 52.9% |
| Kagi LLM Benchmark | — | 73.3% |
| ARC-AGI-1 | — | 86.2% |
| CritPt | 16.9% | — |
| EnigmaEval | — | 10.4% |
| EBR-Bench | — | 23% |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.1 (#21), GPT-5.2: 59.8 (#32)
| Benchmark | Claude Sonnet 5 | GPT-5.2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 65.6% | 67.4% |
| FrontierMath Tier 4 | 29.3% | 31.7% |
| OTIS Mock AIME 2024-2025 | 94.7% | 96.1% |
| ProofBench | 77% | 15% |
| LMArena Math | 1467 | 1439 |
| MathArena Final-Answer Competitions | — | 72% |
| FrontierMath (Feb 2025 set) | — | 40.7% |
| FrontierMath Tier 4 (v1) | — | 18.8% |
Knowledge GPT-5.2 leads
Claude Sonnet 5: 55.7 (#42), GPT-5.2: 59.2 (#29)
| Benchmark | Claude Sonnet 5 | GPT-5.2 |
|---|---|---|
| GPQA Diamond | 90.5% | 91.4% |
| SimpleQA Verified | 33.7% | 37.1% |
| LMArena Expert | 1491 | 1445 |
| Humanity's Last Exam | — | 27.8% |
| Vectara Hallucination Rate | — | 8.4% |
Multimodal GPT-5.2 leads
Claude Sonnet 5: 42.4 (#26), GPT-5.2: 50.9 (#7)
| Benchmark | Claude Sonnet 5 | GPT-5.2 |
|---|---|---|
| LMArena Vision | 1275 | 1268 |
| LMArena Document | 1466 | 1405 |
| VPCT | — | 84% |
| Blueprint-Bench 2 | 24.9% | — |
| Furniture Assembly | — | 38.3% |
Multilingual Too close to call
Claude Sonnet 5: 54.0 (#55), GPT-5.2: 53.6 (#63)
| Benchmark | Claude Sonnet 5 | GPT-5.2 |
|---|---|---|
| LMArena Non-English | 1431 | 1425 |
| LMArena Chinese | 1475 | 1460 |
| LMArena French | 1457 | 1456 |
| LMArena German | 1448 | 1448 |
| LMArena Japanese | 1422 | 1421 |
| LMArena Korean | 1411 | 1390 |
| LMArena Russian | 1452 | 1440 |
| LMArena Spanish | 1436 | 1433 |
Instruction Following Claude Sonnet 5 leads
Claude Sonnet 5: 76.6 (#39), GPT-5.2: 74.9 (#83)
| Benchmark | Claude Sonnet 5 | GPT-5.2 |
|---|---|---|
| LMArena Instruction Following | 1453 | 1417 |
Long Context Too close to call
Claude Sonnet 5: 44.8 (#53), GPT-5.2: 44.0 (#74)
| Benchmark | Claude Sonnet 5 | GPT-5.2 |
|---|---|---|
| LMArena Longer Query | 1464 | 1428 |
| CL-bench | — | 18.2% |
Writing & Preference Claude Sonnet 5 leads
Claude Sonnet 5: 69.4 (#24), GPT-5.2: 67.0 (#30)
| Benchmark | Claude Sonnet 5 | GPT-5.2 |
|---|---|---|
| LMArena Text | 1443 | 1439 |
| LMArena Creative Writing | 1416 | 1402 |
| EQ-Bench Creative Writing | 1794 | 1703 |
| LMArena Multi-Turn | 1454 | 1458 |
| EQ-Bench 4 | 1236 | — |
Frequently asked questions
Is Claude Sonnet 5 better than GPT-5.2?
Claude Sonnet 5 and GPT-5.2 score almost the same on the Noometry Index (54.5 vs 54.1), so choose on price, context window or the category you care about most.
Which is cheaper, Claude Sonnet 5 or GPT-5.2?
Claude Sonnet 5 is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; GPT-5.2 lists at $1.75 and $14.
Is Claude Sonnet 5 or GPT-5.2 better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 52.2 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 5 does, with 1M tokens against 400K.
How many benchmarks do Claude Sonnet 5 and GPT-5.2 share?
40 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and GPT-5.2 has 67.