Model comparison
Claude Sonnet 4.6 vs GPT-5.2
GPT-5.2 is the stronger model overall, scoring 54.1 to 50.1 on the Noometry Index.
Last verified . 44 shared benchmarks.
Summary
- They share 44 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 4 categories and GPT-5.2 in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where GPT-5.2 leads 50.9 to 38.0.
- The biggest single-benchmark swing is Chess Puzzles: 13% for Claude Sonnet 4.6 and 49% for GPT-5.2.
- GPT-5.2 is cheaper at $1.75 / $14 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
- Claude Sonnet 4.6 accepts more context: 1M tokens versus 400K.
Side by side
| Claude Sonnet 4.6 | GPT-5.2 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 50.1 | 54.1 |
| Released | 2026-02-17 | 2025-12-11 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 400K |
| Max output | 128K | 128K |
| Input $ / M tokens | $3 | $1.75 |
| Output $ / M tokens | $15 | $14 |
| Results tracked | 57 | 67 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.2 leads
Claude Sonnet 4.6: 46.0 (#62), GPT-5.2: 52.2 (#32)
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 |
|---|---|---|
| SWE-bench Verified | 75.2% | 73.8% |
| LMArena WebDev | 1521 | 1415 |
| WeirdML | 66.1% | 72.2% |
| LMArena Coding | 1504 | 1447 |
| ALE-Bench | 1,327 | 1,294 |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
| SWE-bench Verified (bash only) | — | 72.8% |
| SWE-bench Multilingual | — | 66.7% |
| SciCode | 46.8% | — |
| GSO | — | 27.4% |
| AlgoTune | — | 2.05 |
Agentic & Tool Use Too close to call
Claude Sonnet 4.6: 39.1 (#26), GPT-5.2: 40.0 (#24)
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 |
|---|---|---|
| Terminal-Bench | 53.4% | 64.9% |
| DeepResearch Bench | 54.9% | 41.1% |
| LMArena Search | 1221 | 1207 |
| Vending-Bench 2 | 7,204 | 3,591 |
| APEX-Agents | 43% | — |
| Berkeley Function Calling Leaderboard | — | 55.9% |
| OSWorld 2.0 | 9.3% | — |
| 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% |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| METR Time Horizons | — | 75.3% |
Reasoning GPT-5.2 leads
Claude Sonnet 4.6: 46.1 (#40), GPT-5.2: 50.1 (#33)
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 |
|---|---|---|
| ARC-AGI-2 | 60.4% | 52.9% |
| NYT Connections (extended) | 80.9% | 83.6% |
| ARC-AGI-1 | 86.5% | 86.2% |
| Chess Puzzles | 13% | 49% |
| LMArena Hard Prompts | 1485 | 1445 |
| Mystery Game Puzzles | 16% | 23% |
| DTBench | 89.9% | 90.9% |
| LMCA | 46.5% | 43.9% |
| Epoch Capabilities Index | 152.25 | 153.45 |
| ForecastBench | 62 | 60.1 |
| SimpleBench | — | 45.8% |
| Kagi LLM Benchmark | — | 73.3% |
| CritPt | 3.1% | — |
| EnigmaEval | — | 10.4% |
| Thematic Generalization | 76.3% | — |
| EBR-Bench | — | 23% |
Math GPT-5.2 leads
Claude Sonnet 4.6: 51.9 (#41), GPT-5.2: 59.8 (#32)
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 96.1% |
| ProofBench | 45% | 15% |
| LMArena Math | 1463 | 1439 |
| FrontierMath (Feb 2025 set) | 32.4% | 40.7% |
| FrontierMath Tier 4 (v1) | 8.3% | 18.8% |
| FrontierMath (Tiers 1-3) | — | 67.4% |
| FrontierMath Tier 4 | — | 31.7% |
| MathArena Final-Answer Competitions | — | 72% |
Knowledge GPT-5.2 leads
Claude Sonnet 4.6: 51.6 (#60), GPT-5.2: 59.2 (#29)
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 |
|---|---|---|
| GPQA Diamond | 87.4% | 91.4% |
| SimpleQA Verified | 35.5% | 37.1% |
| Vectara Hallucination Rate | 10.6% | 8.4% |
| LMArena Expert | 1500 | 1445 |
| Humanity's Last Exam | — | 27.8% |
Multimodal GPT-5.2 leads
Claude Sonnet 4.6: 38.0 (#61), GPT-5.2: 50.9 (#7)
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 |
|---|---|---|
| LMArena Vision | 1283 | 1268 |
| LMArena Document | 1482 | 1405 |
| VPCT | — | 84% |
| Blueprint-Bench 2 | 6.7% | — |
| Furniture Assembly | — | 38.3% |
Multilingual Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 54.6 (#39), GPT-5.2: 53.6 (#63)
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 |
|---|---|---|
| LMArena Non-English | 1440 | 1425 |
| LMArena Chinese | 1491 | 1460 |
| LMArena French | 1465 | 1456 |
| LMArena German | 1428 | 1448 |
| LMArena Japanese | 1419 | 1421 |
| LMArena Korean | 1411 | 1390 |
| LMArena Russian | 1440 | 1440 |
| LMArena Spanish | 1465 | 1433 |
Instruction Following Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 77.6 (#23), GPT-5.2: 74.9 (#83)
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 |
|---|---|---|
| LMArena Instruction Following | 1476 | 1417 |
Long Context Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 45.3 (#40), GPT-5.2: 44.0 (#74)
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 |
|---|---|---|
| LMArena Longer Query | 1479 | 1428 |
| CL-bench | — | 18.2% |
Writing & Preference Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 70.4 (#22), GPT-5.2: 67.0 (#30)
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 |
|---|---|---|
| LMArena Text | 1458 | 1439 |
| LMArena Creative Writing | 1435 | 1402 |
| EQ-Bench Creative Writing | 1810 | 1703 |
| LMArena Multi-Turn | 1464 | 1458 |
| EQ-Bench 4 | 1207 | — |
Frequently asked questions
Is Claude Sonnet 4.6 better than GPT-5.2?
GPT-5.2 is the stronger model overall, scoring 54.1 to 50.1 on the Noometry Index.
Which is cheaper, Claude Sonnet 4.6 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 Sonnet 4.6 lists at $3 and $15.
Is Claude Sonnet 4.6 or GPT-5.2 better for coding?
GPT-5.2 scores higher on coding benchmarks: 52.2 versus 46.0 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 4.6 does, with 1M tokens against 400K.
How many benchmarks do Claude Sonnet 4.6 and GPT-5.2 share?
44 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and GPT-5.2 has 67.