Model comparison
Claude Opus 4.7 vs GPT-5.5 Pro
GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 58.3 on the Noometry Index. Claude Opus 4.7 costs 6.8× less per token, which makes it the better buy when GPT-5.5 Pro's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Summary
- They share 14 benchmarks with published results for both. Claude Opus 4.7 scores higher in 0 categories and GPT-5.5 Pro in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.5 Pro leads 73.3 to 53.8.
- The biggest single-benchmark swing is FrontierMath Tier 4: 31.7% for Claude Opus 4.7 and 78% for GPT-5.5 Pro.
- Claude Opus 4.7 is cheaper at $5 / $25 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 Opus 4.7 | GPT-5.5 Pro | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 58.3 | 64.3 |
| Released | 2026-04-14 | 2026-04-23 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $5 | $30 |
| Output $ / M tokens | $25 | $180 |
| Results tracked | 66 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude Opus 4.7: 59.6 (#13), GPT-5.5 Pro: —
| Benchmark | Claude Opus 4.7 | GPT-5.5 Pro |
|---|---|---|
| SWE-bench Verified | 83.5% | — |
| FrontierCode | 38.5% | — |
| LMArena WebDev | 1558 | — |
| SciCode | 54.5% | — |
| GSO | 44.1% | — |
| WeirdML | 76.4% | — |
| LMArena Coding | 1518 | — |
| MirrorCode | 31.1% | — |
| ALE-Bench | 1,323 | — |
Agentic & Tool Use Not comparable
Claude Opus 4.7: 47.9 (#10), GPT-5.5 Pro: —
| Benchmark | Claude Opus 4.7 | GPT-5.5 Pro |
|---|---|---|
| Terminal-Bench | 80.2% | — |
| APEX-Agents | 49.2% | — |
| OSWorld 2.0 | 18.2% | — |
| τ²-bench Banking | 40.2% | — |
| PostTrainBench | 28.6% | — |
| ExploitBench | 26.5% | — |
| GBAEval | 43.8% | — |
| GDP.pdf | 21% | — |
| LMArena Search | 1233 | — |
| Vending-Bench 2 | 10,937 | — |
Reasoning GPT-5.5 Pro leads
Claude Opus 4.7: 53.8 (#29), GPT-5.5 Pro: 73.3 (#10)
| Benchmark | Claude Opus 4.7 | GPT-5.5 Pro |
|---|---|---|
| ARC-AGI-2 | 75.8% | 84.6% |
| SimpleBench | 61.7% | 76.9% |
| ARC-AGI-1 | 93.5% | 96.5% |
| CritPt | 12% | 30.6% |
| Chess Puzzles | 30% | 64% |
| DTBench | 94.7% | 96% |
| LMCA | 52.2% | 53.9% |
| Epoch Capabilities Index | 156.25 | 162.07 |
| Kagi LLM Benchmark | 80.7% | — |
| NYT Connections (extended) | 39% | — |
| Thematic Generalization | 72.8% | — |
| EBR-Bench | 19% | — |
| LMArena Hard Prompts | 1506 | — |
| Mystery Game Puzzles | 28% | — |
| ForecastBench | 60.3 | — |
Math GPT-5.5 Pro leads
Claude Opus 4.7: 66.7 (#26), GPT-5.5 Pro: 84.0 (#10)
| Benchmark | Claude Opus 4.7 | GPT-5.5 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 70.2% | 87.7% |
| FrontierMath Tier 4 | 31.7% | 78% |
| OTIS Mock AIME 2024-2025 | 97.8% | 100% |
| FrontierMath (Feb 2025 set) | 43.8% | 52.4% |
| FrontierMath Tier 4 (v1) | 22.9% | 39.6% |
| MathArena Final-Answer Competitions | 73.6% | — |
| ProofBench | 54% | — |
| LMArena Math | 1499 | — |
Knowledge GPT-5.5 Pro leads
Claude Opus 4.7: 62.6 (#23), GPT-5.5 Pro: 64.1 (#19)
| Benchmark | Claude Opus 4.7 | GPT-5.5 Pro |
|---|---|---|
| GPQA Diamond | 90.2% | 93.9% |
| Humanity's Last Exam | 36.2% | — |
| SimpleQA Verified | 51.7% | — |
| Vectara Hallucination Rate | 12% | — |
| LMArena Expert | 1521 | — |
Multimodal Not comparable
Claude Opus 4.7: 41.2 (#38), GPT-5.5 Pro: —
| Benchmark | Claude Opus 4.7 | GPT-5.5 Pro |
|---|---|---|
| LMArena Vision | 1316 | — |
| Blueprint-Bench 2 | 24.5% | — |
| Furniture Assembly | 33.3% | — |
| LMArena Document | 1495 | — |
Multilingual Not comparable
Claude Opus 4.7: 57.3 (#10), GPT-5.5 Pro: —
| Benchmark | Claude Opus 4.7 | GPT-5.5 Pro |
|---|---|---|
| LMArena Non-English | 1480 | — |
| LMArena Chinese | 1531 | — |
| LMArena French | 1503 | — |
| LMArena German | 1495 | — |
| LMArena Japanese | 1472 | — |
| LMArena Korean | 1464 | — |
| LMArena Russian | 1494 | — |
| LMArena Spanish | 1495 | — |
Instruction Following Not comparable
Claude Opus 4.7: 78.4 (#10), GPT-5.5 Pro: —
| Benchmark | Claude Opus 4.7 | GPT-5.5 Pro |
|---|---|---|
| LMArena Instruction Following | 1498 | — |
Long Context Not comparable
Claude Opus 4.7: 46.2 (#25), GPT-5.5 Pro: —
| Benchmark | Claude Opus 4.7 | GPT-5.5 Pro |
|---|---|---|
| LMArena Longer Query | 1505 | — |
Writing & Preference Not comparable
Claude Opus 4.7: 75.1 (#8), GPT-5.5 Pro: —
| Benchmark | Claude Opus 4.7 | GPT-5.5 Pro |
|---|---|---|
| LMArena Text | 1490 | — |
| LMArena Creative Writing | 1486 | — |
| EQ-Bench Creative Writing | 1914 | — |
| EQ-Bench 4 | 1311 | — |
| LMArena Multi-Turn | 1505 | — |
Frequently asked questions
Is Claude Opus 4.7 better than GPT-5.5 Pro?
GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 58.3 on the Noometry Index. Claude Opus 4.7 costs 6.8× 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 Opus 4.7 or GPT-5.5 Pro?
Claude Opus 4.7 is cheaper. It lists at $5 per million input tokens and $25 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 Opus 4.7 and GPT-5.5 Pro share?
14 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and GPT-5.5 Pro has 14.