Model comparison
Claude Opus 4.1 vs GPT-5.5
GPT-5.5 is the stronger model overall, scoring 63.4 to 40.8 on the Noometry Index.
Last verified . 39 shared benchmarks.
Summary
- They share 39 benchmarks with published results for both. Claude Opus 4.1 scores higher in 0 categories and GPT-5.5 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.5 leads 81.5 to 22.0.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 12.6% for Claude Opus 4.1 and 85.3% for GPT-5.5.
- GPT-5.5 is cheaper at $5 / $30 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- GPT-5.5 accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Opus 4.1 | GPT-5.5 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 40.8 | 63.4 |
| Released | 2025-08-05 | 2026-04-23 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 32K | 128K |
| Input $ / M tokens | $15 | $5 |
| Output $ / M tokens | $75 | $30 |
| Results tracked | 48 | 71 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.5 leads
Claude Opus 4.1: 44.3 (#69), GPT-5.5: 58.3 (#13)
| Benchmark | Claude Opus 4.1 | GPT-5.5 |
|---|---|---|
| SWE-bench Verified | 73.3% | 80.6% |
| LMArena WebDev | 1390 | 1512 |
| WeirdML | 45.9% | 84.9% |
| LMArena Coding | 1479 | 1494 |
| ALE-Bench | 674.77 | 1,943 |
| DeepSWE | — | 67% |
| FrontierCode | — | 43% |
| SciCode | — | 56.1% |
| GSO | — | 40.2% |
| MirrorCode | — | 10% |
| AlgoTune | 1.34 | — |
Agentic & Tool Use GPT-5.5 leads
Claude Opus 4.1: 34.8 (#38), GPT-5.5: 50.7 (#6)
| Benchmark | Claude Opus 4.1 | GPT-5.5 |
|---|---|---|
| Terminal-Bench | 38% | 84.7% |
| DeepResearch Bench | 48.3% | 54% |
| LMArena Search | 1148 | 1242 |
| APEX-Agents | — | 55.1% |
| OSWorld 2.0 | — | 13% |
| GDPval | 43.6% | — |
| Remote Labor Index | — | 6.3% |
| τ²-bench Banking | — | 44.6% |
| Cybench | 42% | — |
| PostTrainBench | — | 27.2% |
| ExploitBench | — | 47.4% |
| GBAEval | — | 53.2% |
| GDP.pdf | — | 26% |
| METR Time Horizons | 66.8% | — |
| Vending-Bench 2 | — | 7,524 |
Reasoning GPT-5.5 leads
Claude Opus 4.1: 31.6 (#70), GPT-5.5: 72.7 (#8)
| Benchmark | Claude Opus 4.1 | GPT-5.5 |
|---|---|---|
| SimpleBench | 60% | 69% |
| Chess Puzzles | 7% | 54% |
| EBR-Bench | 7.9% | 34.3% |
| LMArena Hard Prompts | 1443 | 1489 |
| Mystery Game Puzzles | 21% | 56% |
| DTBench | 80% | 96% |
| LMCA | 37.1% | 54.3% |
| Epoch Capabilities Index | 144.11 | 159.25 |
| ForecastBench | 62 | 60.6 |
| ARC-AGI-2 | — | 85% |
| Kagi LLM Benchmark | — | 88.8% |
| NYT Connections (extended) | — | 96.2% |
| ARC-AGI-1 | — | 95% |
| CritPt | — | 27.1% |
| EnigmaEval | 7.2% | — |
| Surface Evolver Bench | — | 88.1% |
| Bench to the Future 3 | — | 0.14 |
Math GPT-5.5 leads
Claude Opus 4.1: 22.0 (#267), GPT-5.5: 81.5 (#9)
| Benchmark | Claude Opus 4.1 | GPT-5.5 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 12.6% | 85.3% |
| FrontierMath Tier 4 | 2.4% | 72.5% |
| OTIS Mock AIME 2024-2025 | 68.9% | 100% |
| LMArena Math | 1430 | 1486 |
| FrontierMath (Feb 2025 set) | 7.2% | 51.7% |
| FrontierMath Tier 4 (v1) | 4.2% | 35.4% |
| MathArena Final-Answer Competitions | — | 94.3% |
| ProofBench | — | 50% |
| FrontierMath Erdős | — | 0% |
Knowledge GPT-5.5 leads
Claude Opus 4.1: 41.9 (#93), GPT-5.5: 64.4 (#14)
| Benchmark | Claude Opus 4.1 | GPT-5.5 |
|---|---|---|
| GPQA Diamond | 77.3% | 94% |
| Vectara Hallucination Rate | 11.8% | 9.3% |
| LMArena Expert | 1439 | 1508 |
| Humanity's Last Exam | 11.5% | — |
| SimpleQA Verified | — | 63% |
| Confabulations | 17.1% | — |
Multimodal GPT-5.5 leads
Claude Opus 4.1: 26.2 (#114), GPT-5.5: 47.1 (#11)
| Benchmark | Claude Opus 4.1 | GPT-5.5 |
|---|---|---|
| LMArena Vision | — | 1297 |
| VPCT | 35% | — |
| Blueprint-Bench 2 | — | 36.2% |
| Furniture Assembly | — | 44.2% |
| LMArena Document | — | 1486 |
Multilingual GPT-5.5 leads
Claude Opus 4.1: 52.1 (#90), GPT-5.5: 56.5 (#19)
| Benchmark | Claude Opus 4.1 | GPT-5.5 |
|---|---|---|
| LMArena Non-English | 1405 | 1467 |
| LMArena Chinese | 1427 | 1535 |
| LMArena French | 1432 | 1486 |
| LMArena German | 1412 | 1478 |
| LMArena Japanese | 1378 | 1498 |
| LMArena Korean | 1381 | 1461 |
| LMArena Russian | 1421 | 1473 |
| LMArena Spanish | 1448 | 1469 |
Instruction Following GPT-5.5 leads
Claude Opus 4.1: 75.8 (#53), GPT-5.5: 77.7 (#18)
| Benchmark | Claude Opus 4.1 | GPT-5.5 |
|---|---|---|
| LMArena Instruction Following | 1436 | 1479 |
Long Context GPT-5.5 leads
Claude Opus 4.1: 44.5 (#60), GPT-5.5: 48.3 (#12)
| Benchmark | Claude Opus 4.1 | GPT-5.5 |
|---|---|---|
| LMArena Longer Query | 1455 | 1484 |
| CL-bench Life | — | 22.2% |
Writing & Preference GPT-5.5 leads
Claude Opus 4.1: 62.6 (#70), GPT-5.5: 72.8 (#13)
| Benchmark | Claude Opus 4.1 | GPT-5.5 |
|---|---|---|
| LMArena Text | 1419 | 1471 |
| LMArena Creative Writing | 1412 | 1455 |
| LMArena Multi-Turn | 1444 | 1477 |
| Short-Story Creative Writing | 84.7% | — |
| EQ-Bench Creative Writing | — | 1844 |
| EQ-Bench 4 | — | 1315 |
Frequently asked questions
Is Claude Opus 4.1 better than GPT-5.5?
GPT-5.5 is the stronger model overall, scoring 63.4 to 40.8 on the Noometry Index.
Which is cheaper, Claude Opus 4.1 or GPT-5.5?
GPT-5.5 is cheaper. It lists at $5 per million input tokens and $30 per million output tokens; Claude Opus 4.1 lists at $15 and $75.
Is Claude Opus 4.1 or GPT-5.5 better for coding?
GPT-5.5 scores higher on coding benchmarks: 58.3 versus 44.3 in the Noometry coding category.
Which has the bigger context window?
GPT-5.5 does, with 1.05M tokens against 200K.
How many benchmarks do Claude Opus 4.1 and GPT-5.5 share?
39 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and GPT-5.5 has 71.