Model comparison
Claude Sonnet 4.6 vs GPT-5.2 Pro
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 50.3 on the Noometry Index. Claude Sonnet 4.6 costs 9.6× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
Summary
- They share 5 benchmarks with published results for both. Claude Sonnet 4.6 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 65.3 to 52.9.
- The biggest single-benchmark swing is ARC-AGI-2: 60.4% for Claude Sonnet 4.6 and 54.2% for GPT-5.2 Pro.
- Claude Sonnet 4.6 is cheaper at $3 / $15 per million input/output tokens, against $21 / $168 for GPT-5.2 Pro.
- Claude Sonnet 4.6 accepts more context: 1M tokens versus 400K.
Side by side
| Claude Sonnet 4.6 | GPT-5.2 Pro | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 50.3 | 52.3 |
| Released | 2026-02-17 | 2025-12-11 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 400K |
| Max output | 128K | 128K |
| Input $ / M tokens | $3 | $21 |
| Output $ / M tokens | $15 | $168 |
| Results tracked | 57 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude Sonnet 4.6: 46.3 (#67), GPT-5.2 Pro: —
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 Pro |
|---|---|---|
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
| LMArena WebDev | 1522 | — |
| SciCode | 46.8% | — |
| WeirdML | 66.1% | — |
| LMArena Coding | 1504 | — |
| ALE-Bench | 1,327 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4.6: 39.1 (#28), GPT-5.2 Pro: —
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 Pro |
|---|---|---|
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| OSWorld 2.0 | 9.3% | — |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| LMArena Search | 1221 | — |
| Vending-Bench 2 | 7,204 | — |
Reasoning GPT-5.2 Pro leads
Claude Sonnet 4.6: 46.1 (#45), GPT-5.2 Pro: 51.5 (#33)
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 Pro |
|---|---|---|
| ARC-AGI-2 | 60.4% | 54.2% |
| NYT Connections (extended) | 80.9% | 79.3% |
| ARC-AGI-1 | 86.5% | 90.5% |
| Epoch Capabilities Index | 152.24 | 155.4 |
| SimpleBench | — | 57.4% |
| CritPt | 3.1% | — |
| Chess Puzzles | 13% | — |
| Thematic Generalization | 76.3% | — |
| LMArena Hard Prompts | 1484 | — |
| Mystery Game Puzzles | 16% | — |
| DTBench | 89.9% | — |
| LMCA | 46.5% | — |
| ForecastBench | 62 | — |
Math GPT-5.2 Pro leads
Claude Sonnet 4.6: 52.9 (#49), GPT-5.2 Pro: 65.3 (#29)
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 Pro |
|---|---|---|
| FrontierMath Tier 4 (v1) | 8.3% | 31.3% |
| FrontierMath (Tiers 1-3) | — | 74% |
| FrontierMath Tier 4 | — | 46% |
| OTIS Mock AIME 2024-2025 | 85.8% | — |
| ProofBench | 45% | — |
| LMArena Math | 1462 | — |
| FrontierMath (Feb 2025 set) | 32.4% | — |
Knowledge Not comparable
Claude Sonnet 4.6: 51.7 (#65), GPT-5.2 Pro: —
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 Pro |
|---|---|---|
| GPQA Diamond | 87.4% | — |
| SimpleQA Verified | 35.5% | — |
| Vectara Hallucination Rate | 10.6% | — |
| LMArena Expert | 1500 | — |
Multimodal Not comparable
Claude Sonnet 4.6: 38.0 (#68), GPT-5.2 Pro: —
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 Pro |
|---|---|---|
| LMArena Vision | 1283 | — |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |
Multilingual Not comparable
Claude Sonnet 4.6: 54.4 (#41), GPT-5.2 Pro: —
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 Pro |
|---|---|---|
| LMArena Non-English | 1440 | — |
| LMArena Chinese | 1491 | — |
| LMArena French | 1465 | — |
| LMArena German | 1428 | — |
| LMArena Japanese | 1420 | — |
| LMArena Korean | 1411 | — |
| LMArena Russian | 1440 | — |
| LMArena Spanish | 1464 | — |
Instruction Following Not comparable
Claude Sonnet 4.6: 77.4 (#25), GPT-5.2 Pro: —
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 Pro |
|---|---|---|
| LMArena Instruction Following | 1475 | — |
Long Context Not comparable
Claude Sonnet 4.6: 45.3 (#44), GPT-5.2 Pro: —
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 Pro |
|---|---|---|
| LMArena Longer Query | 1479 | — |
Writing & Preference Not comparable
Claude Sonnet 4.6: 70.2 (#22), GPT-5.2 Pro: —
| Benchmark | Claude Sonnet 4.6 | GPT-5.2 Pro |
|---|---|---|
| LMArena Text | 1458 | — |
| LMArena Creative Writing | 1435 | — |
| EQ-Bench Creative Writing | 1810 | — |
| EQ-Bench 4 | 1207 | — |
| LMArena Multi-Turn | 1464 | — |
Frequently asked questions
Is Claude Sonnet 4.6 better than GPT-5.2 Pro?
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 50.3 on the Noometry Index. Claude Sonnet 4.6 costs 9.6× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4.6 or GPT-5.2 Pro?
Claude Sonnet 4.6 is cheaper. It lists at $3 per million input tokens and $15 per million output tokens; GPT-5.2 Pro lists at $21 and $168.
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 Pro share?
5 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and GPT-5.2 Pro has 8.