Model comparison
Claude Opus 4.5 vs GPT-4.1
Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 35.9 on the Noometry Index. GPT-4.1 costs 2.9× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.
Last verified . 42 shared benchmarks.
Summary
- They share 42 benchmarks with published results for both. Claude Opus 4.5 scores higher in 9 categories and GPT-4.1 in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 4.5 leads 42.6 to 11.7.
- The biggest single-benchmark swing is ARC-AGI-1: 80% for Claude Opus 4.5 and 5.5% for GPT-4.1.
- GPT-4.1 is cheaper at $2 / $8 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
- GPT-4.1 accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Opus 4.5 | GPT-4.1 | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 50.5 | 35.9 |
| Released | 2025-11-01 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 64K | 33K |
| Input $ / M tokens | $5 | $2 |
| Output $ / M tokens | $25 | $8 |
| Results tracked | 69 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.5 leads
Claude Opus 4.5: 54.8 (#27), GPT-4.1: 34.4 (#238)
| Benchmark | Claude Opus 4.5 | GPT-4.1 |
|---|---|---|
| SWE-bench Verified | 76.7% | 48.5% |
| SWE-bench Verified (bash only) | 76.8% | 39.6% |
| WeirdML | 63.7% | 39% |
| LMArena Coding | 1504 | 1391 |
| ALE-Bench | 1,025 | 558.1 |
| Aider Polyglot | — | 52.4% |
| LMArena WebDev | 1494 | — |
| SWE-bench Multilingual | 70.7% | — |
| GSO | 26.5% | — |
| CadEval | — | 42% |
| AlgoTune | 1.77 | — |
Agentic & Tool Use Claude Opus 4.5 leads
Claude Opus 4.5: 47.3 (#12), GPT-4.1: 34.7 (#43)
| Benchmark | Claude Opus 4.5 | GPT-4.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 77.5% | 54% |
| Terminal-Bench | 63.1% | — |
| GDPval | 45.5% | — |
| Remote Labor Index | 3.8% | — |
| τ²-bench Airline | 84% | — |
| τ²-bench Banking | 24.7% | — |
| τ²-bench Retail | 79.6% | — |
| τ²-bench Telecom | 92.3% | — |
| Cybench | 82% | — |
| DeepResearch Bench | 54.8% | — |
| OSWorld | 66.3% | — |
| BALROG | 43.5% | — |
| LMArena Search | 1180 | — |
| METR Time Horizons | 75% | — |
| Vending-Bench 2 | 4,967 | — |
Reasoning Claude Opus 4.5 leads
Claude Opus 4.5: 42.6 (#51), GPT-4.1: 11.7 (#339)
| Benchmark | Claude Opus 4.5 | GPT-4.1 |
|---|---|---|
| ARC-AGI-2 | 37.6% | 0.4% |
| SimpleBench | 62% | 27% |
| Kagi LLM Benchmark | 80.2% | 52.3% |
| ARC-AGI-1 | 80% | 5.5% |
| Chess Puzzles | 12% | 6% |
| EnigmaEval | 11.9% | 2.2% |
| LMArena Hard Prompts | 1476 | 1384 |
| DTBench | 89.9% | 68.3% |
| LMCA | 44.5% | 25.6% |
| Epoch Capabilities Index | 150.09 | 136.78 |
| ForecastBench | 60.7 | 61.5 |
| NYT Connections (extended) | 52.5% | — |
| EBR-Bench | 14.3% | — |
| Mystery Game Puzzles | 22% | — |
Math Claude Opus 4.5 leads
Claude Opus 4.5: 38.6 (#132), GPT-4.1: 22.3 (#280)
| Benchmark | Claude Opus 4.5 | GPT-4.1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 34.4% | 6% |
| OTIS Mock AIME 2024-2025 | 86.1% | 38.3% |
| LMArena Math | 1463 | 1370 |
| FrontierMath (Feb 2025 set) | 20.7% | 5.5% |
| FrontierMath Tier 4 (v1) | 4.2% | 0% |
| FrontierMath Tier 4 | 4.9% | — |
| ProofBench | 36% | — |
| Omni-MATH | — | 47.1% |
| MATH Level 5 | — | 83% |
Knowledge Claude Opus 4.5 leads
Claude Opus 4.5: 56.5 (#44), GPT-4.1: 37.1 (#160)
| Benchmark | Claude Opus 4.5 | GPT-4.1 |
|---|---|---|
| GPQA Diamond | 86% | 66.9% |
| Humanity's Last Exam | 25.2% | 5.4% |
| SimpleQA Verified | 45.7% | 31.1% |
| Vectara Hallucination Rate | 10.9% | 5.6% |
| LMArena Expert | 1487 | 1364 |
| MMLU-Pro | — | 81.1% |
| GPQA (HELM) | — | 65.9% |
Multimodal GPT-4.1 leads
Claude Opus 4.5: 31.4 (#107), GPT-4.1: 38.2 (#67)
| Benchmark | Claude Opus 4.5 | GPT-4.1 |
|---|---|---|
| GeoBench | 75% | 72% |
| LMArena Vision | — | 1211 |
| VPCT | 40% | — |
| Furniture Assembly | 28.3% | — |
| LMArena Document | 1462 | — |
Multilingual Claude Opus 4.5 leads
Claude Opus 4.5: 54.3 (#47), GPT-4.1: 49.4 (#133)
| Benchmark | Claude Opus 4.5 | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1438 | 1370 |
| LMArena Chinese | 1470 | 1382 |
| LMArena French | 1471 | 1382 |
| LMArena German | 1449 | 1381 |
| LMArena Japanese | 1416 | 1319 |
| LMArena Korean | 1424 | 1339 |
| LMArena Russian | 1447 | 1377 |
| LMArena Spanish | 1458 | 1376 |
Instruction Following Claude Opus 4.5 leads
Claude Opus 4.5: 77.5 (#19), GPT-4.1: 71.3 (#153)
| Benchmark | Claude Opus 4.5 | GPT-4.1 |
|---|---|---|
| LMArena Instruction Following | 1478 | 1367 |
| IFEval | — | 83.8% |
Long Context Claude Opus 4.5 leads
Claude Opus 4.5: 46.5 (#22), GPT-4.1: 40.0 (#163)
| Benchmark | Claude Opus 4.5 | GPT-4.1 |
|---|---|---|
| LMArena Longer Query | 1480 | 1385 |
| Fiction.LiveBench | — | 63.9% |
| CL-bench | 21.1% | — |
Writing & Preference Claude Opus 4.5 leads
Claude Opus 4.5: 68.1 (#28), GPT-4.1: 57.6 (#125)
| Benchmark | Claude Opus 4.5 | GPT-4.1 |
|---|---|---|
| LMArena Text | 1451 | 1383 |
| LMArena Creative Writing | 1445 | 1363 |
| EQ-Bench Creative Writing | 1687 | 1420 |
| LMArena Multi-Turn | 1466 | 1398 |
| WildBench | — | 85.4% |
Frequently asked questions
Is Claude Opus 4.5 better than GPT-4.1?
Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 35.9 on the Noometry Index. GPT-4.1 costs 2.9× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4.5 or GPT-4.1?
GPT-4.1 is cheaper. It lists at $2 per million input tokens and $8 per million output tokens; Claude Opus 4.5 lists at $5 and $25.
Is Claude Opus 4.5 or GPT-4.1 better for coding?
Claude Opus 4.5 scores higher on coding benchmarks: 54.8 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 200K.
How many benchmarks do Claude Opus 4.5 and GPT-4.1 share?
42 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and GPT-4.1 has 52.