Model comparison
Claude Sonnet 5.5 vs GPT-5.5 Pro
GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 61.9 on the Noometry Index. Claude Sonnet 5.5 costs 17× less per token, which makes it the better buy when GPT-5.5 Pro's lead doesn't matter for your workload.
Last verified . 6 shared benchmarks.
Summary
- They share 6 benchmarks with published results for both. Claude Sonnet 5.5 scores higher in 2 categories and GPT-5.5 Pro in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.5 Pro leads 73.3 to 54.0.
- Claude Sonnet 5.5 is cheaper at $2 / $10 per million input/output tokens, against $30 / $180 for GPT-5.5 Pro.
- GPT-5.5 Pro accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Sonnet 5.5 | GPT-5.5 Pro | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 61.9 | 64.3 |
| Released | 2026-09-28 | 2026-04-23 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $2 | $30 |
| Output $ / M tokens | $10 | $180 |
| Results tracked | 32 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude Sonnet 5.5: 67.3 (#6), GPT-5.5 Pro: —
| Benchmark | Claude Sonnet 5.5 | GPT-5.5 Pro |
|---|---|---|
| FrontierCode | 52.1% | — |
| CursorBench | 55.5% | — |
| LMArena WebDev | 1774 | — |
| FrontierSWE | 61.9% | — |
| SciCode | 61% | — |
| LMArena Coding | 1513 | — |
| ALE-Bench | 1,819 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 5.5: 45.0 (#16), GPT-5.5 Pro: —
| Benchmark | Claude Sonnet 5.5 | GPT-5.5 Pro |
|---|---|---|
| APEX-Agents | 75.5% | — |
Reasoning GPT-5.5 Pro leads
Claude Sonnet 5.5: 54.0 (#28), GPT-5.5 Pro: 73.3 (#10)
| Benchmark | Claude Sonnet 5.5 | GPT-5.5 Pro |
|---|---|---|
| CritPt | 31.4% | 30.6% |
| Epoch Capabilities Index | 165.03 | 162.07 |
| ARC-AGI-2 | — | 84.6% |
| SimpleBench | — | 76.9% |
| NYT Connections (extended) | 80.5% | — |
| ARC-AGI-1 | — | 96.5% |
| Chess Puzzles | — | 64% |
| LMArena Hard Prompts | 1495 | — |
| Mystery Game Puzzles | 65% | — |
| DTBench | — | 96% |
| LMCA | — | 53.9% |
Math Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 87.9 (#6), GPT-5.5 Pro: 84.0 (#10)
| Benchmark | Claude Sonnet 5.5 | GPT-5.5 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 88.8% | 87.7% |
| FrontierMath Tier 4 | 80.5% | 78% |
| OTIS Mock AIME 2024-2025 | 100% | 100% |
| ProofBench | 100% | — |
| LMArena Math | 1510 | — |
| FrontierMath (Feb 2025 set) | — | 52.4% |
| FrontierMath Erdős | 2.9% | — |
| FrontierMath Tier 4 (v1) | — | 39.6% |
Knowledge Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 66.0 (#12), GPT-5.5 Pro: 64.1 (#19)
| Benchmark | Claude Sonnet 5.5 | GPT-5.5 Pro |
|---|---|---|
| GPQA Diamond | 95.6% | 93.9% |
| SimpleQA Verified | 46.5% | — |
| LMArena Expert | 1540 | — |
Multimodal Not comparable
Claude Sonnet 5.5: 51.5 (#6), GPT-5.5 Pro: —
| Benchmark | Claude Sonnet 5.5 | GPT-5.5 Pro |
|---|---|---|
| LMArena Vision | 1289 | — |
| Furniture Assembly | 75% | — |
Multilingual Not comparable
Claude Sonnet 5.5: 55.3 (#30), GPT-5.5 Pro: —
| Benchmark | Claude Sonnet 5.5 | GPT-5.5 Pro |
|---|---|---|
| LMArena Non-English | 1452 | — |
| LMArena Chinese | 1522 | — |
| LMArena Russian | 1451 | — |
Instruction Following Not comparable
Claude Sonnet 5.5: 78.3 (#11), GPT-5.5 Pro: —
| Benchmark | Claude Sonnet 5.5 | GPT-5.5 Pro |
|---|---|---|
| LMArena Instruction Following | 1495 | — |
Long Context Not comparable
Claude Sonnet 5.5: 45.9 (#28), GPT-5.5 Pro: —
| Benchmark | Claude Sonnet 5.5 | GPT-5.5 Pro |
|---|---|---|
| LMArena Longer Query | 1498 | — |
Writing & Preference Not comparable
Claude Sonnet 5.5: 66.0 (#40), GPT-5.5 Pro: —
| Benchmark | Claude Sonnet 5.5 | GPT-5.5 Pro |
|---|---|---|
| LMArena Text | 1471 | — |
| LMArena Creative Writing | 1465 | — |
| LMArena Multi-Turn | 1474 | — |
Frequently asked questions
Is Claude Sonnet 5.5 better than GPT-5.5 Pro?
GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 61.9 on the Noometry Index. Claude Sonnet 5.5 costs 17× less per token, which makes it the better buy when GPT-5.5 Pro's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 5.5 or GPT-5.5 Pro?
Claude Sonnet 5.5 is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; GPT-5.5 Pro lists at $30 and $180.
Which has the bigger context window?
GPT-5.5 Pro does, with 1.05M tokens against 1M.
How many benchmarks do Claude Sonnet 5.5 and GPT-5.5 Pro share?
6 benchmarks have published results for both models. Claude Sonnet 5.5 has 32 scored results on Noometry and GPT-5.5 Pro has 14.