Model comparison
Claude Opus 4.7 vs GPT-5.4
GPT-5.4 is the stronger model overall, scoring 59.4 to 58.3 on the Noometry Index.
Last verified . 61 shared benchmarks.
Summary
- They share 61 benchmarks with published results for both. Claude Opus 4.7 scores higher in 5 categories and GPT-5.4 in 5 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 leads 61.8 to 53.8.
- The biggest single-benchmark swing is NYT Connections (extended): 39% for Claude Opus 4.7 and 91.3% for GPT-5.4.
- GPT-5.4 is cheaper at $2.50 / $15 per million input/output tokens, against $5 / $25 for Claude Opus 4.7.
- GPT-5.4 accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Opus 4.7 | GPT-5.4 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 58.3 | 59.4 |
| Released | 2026-04-14 | 2026-03-05 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $5 | $2.50 |
| Output $ / M tokens | $25 | $15 |
| Results tracked | 66 | 68 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.7 leads
Claude Opus 4.7: 59.6 (#13), GPT-5.4: 52.6 (#33)
| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| SWE-bench Verified | 83.5% | 76.9% |
| LMArena WebDev | 1558 | 1465 |
| SciCode | 54.5% | 56.6% |
| GSO | 44.1% | 31.4% |
| WeirdML | 76.4% | 77.7% |
| LMArena Coding | 1518 | 1497 |
| MirrorCode | 31.1% | 15.6% |
| ALE-Bench | 1,323 | 1,607 |
| DeepSWE | — | 51.8% |
| FrontierCode | 38.5% | — |
| AlgoTune | — | 1.85 |
Agentic & Tool Use Claude Opus 4.7 leads
Claude Opus 4.7: 47.9 (#10), GPT-5.4: 46.5 (#13)
| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| Terminal-Bench | 80.2% | 81.8% |
| APEX-Agents | 49.2% | 52.4% |
| τ²-bench Banking | 40.2% | 39.4% |
| PostTrainBench | 28.6% | 19% |
| GBAEval | 43.8% | 45.1% |
| LMArena Search | 1233 | 1197 |
| Vending-Bench 2 | 10,937 | 6,144 |
| OSWorld 2.0 | 18.2% | — |
| DeepResearch Bench | — | 35.1% |
| ExploitBench | 26.5% | — |
| GDP.pdf | 21% | — |
| METR Time Horizons | — | 74.3% |
Reasoning GPT-5.4 leads
Claude Opus 4.7: 53.8 (#29), GPT-5.4: 61.8 (#19)
| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| ARC-AGI-2 | 75.8% | 74% |
| Kagi LLM Benchmark | 80.7% | 63.8% |
| NYT Connections (extended) | 39% | 91.3% |
| ARC-AGI-1 | 93.5% | 93.7% |
| CritPt | 12% | 23.4% |
| Chess Puzzles | 30% | 44% |
| Thematic Generalization | 72.8% | 80% |
| EBR-Bench | 19% | 25.4% |
| LMArena Hard Prompts | 1506 | 1485 |
| Mystery Game Puzzles | 28% | 37% |
| DTBench | 94.7% | 94.4% |
| LMCA | 52.2% | 52% |
| Epoch Capabilities Index | 156.25 | 156.81 |
| ForecastBench | 60.3 | 59.5 |
| SimpleBench | 61.7% | — |
| EnigmaEval | — | 16% |
Math GPT-5.4 leads
Claude Opus 4.7: 66.7 (#26), GPT-5.4: 73.5 (#19)
| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 70.2% | 78.6% |
| FrontierMath Tier 4 | 31.7% | 49% |
| MathArena Final-Answer Competitions | 73.6% | 83.1% |
| OTIS Mock AIME 2024-2025 | 97.8% | 97.8% |
| ProofBench | 54% | 56% |
| LMArena Math | 1499 | 1488 |
| FrontierMath (Feb 2025 set) | 43.8% | 47.6% |
| FrontierMath Tier 4 (v1) | 22.9% | 27.1% |
Knowledge GPT-5.4 leads
Claude Opus 4.7: 62.6 (#23), GPT-5.4: 65.3 (#14)
| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| GPQA Diamond | 90.2% | 93.3% |
| Humanity's Last Exam | 36.2% | 36.2% |
| SimpleQA Verified | 51.7% | 45.1% |
| Vectara Hallucination Rate | 12% | 7% |
| LMArena Expert | 1521 | 1507 |
Multimodal GPT-5.4 leads
Claude Opus 4.7: 41.2 (#38), GPT-5.4: 43.7 (#20)
| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| LMArena Vision | 1316 | 1303 |
| Blueprint-Bench 2 | 24.5% | 27.1% |
| Furniture Assembly | 33.3% | 37.5% |
| LMArena Document | 1495 | 1471 |
Multilingual Claude Opus 4.7 leads
Claude Opus 4.7: 57.3 (#10), GPT-5.4: 56.2 (#23)
| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| LMArena Non-English | 1480 | 1465 |
| LMArena Chinese | 1531 | 1519 |
| LMArena French | 1503 | 1493 |
| LMArena German | 1495 | 1472 |
| LMArena Japanese | 1472 | 1485 |
| LMArena Korean | 1464 | 1448 |
| LMArena Russian | 1494 | 1480 |
| LMArena Spanish | 1495 | 1454 |
Instruction Following Claude Opus 4.7 leads
Claude Opus 4.7: 78.4 (#10), GPT-5.4: 77.1 (#27)
| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| LMArena Instruction Following | 1498 | 1469 |
Long Context GPT-5.4 leads
Claude Opus 4.7: 46.2 (#25), GPT-5.4: 50.3 (#8)
| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| LMArena Longer Query | 1505 | 1473 |
| CL-bench | — | 27.9% |
| CL-bench Life | — | 21.7% |
Writing & Preference Claude Opus 4.7 leads
Claude Opus 4.7: 75.1 (#8), GPT-5.4: 71.9 (#17)
| Benchmark | Claude Opus 4.7 | GPT-5.4 |
|---|---|---|
| LMArena Text | 1490 | 1469 |
| LMArena Creative Writing | 1486 | 1439 |
| EQ-Bench Creative Writing | 1914 | 1840 |
| EQ-Bench 4 | 1311 | 1272 |
| LMArena Multi-Turn | 1505 | 1482 |
Frequently asked questions
Is Claude Opus 4.7 better than GPT-5.4?
GPT-5.4 is the stronger model overall, scoring 59.4 to 58.3 on the Noometry Index.
Which is cheaper, Claude Opus 4.7 or GPT-5.4?
GPT-5.4 is cheaper. It lists at $2.50 per million input tokens and $15 per million output tokens; Claude Opus 4.7 lists at $5 and $25.
Is Claude Opus 4.7 or GPT-5.4 better for coding?
Claude Opus 4.7 scores higher on coding benchmarks: 59.6 versus 52.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 does, with 1.05M tokens against 1M.
How many benchmarks do Claude Opus 4.7 and GPT-5.4 share?
61 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and GPT-5.4 has 68.