Model comparison
Claude Opus 4 vs GPT-4.1 nano
Claude Opus 4 is the stronger model overall, scoring 42.9 to 27.7 on the Noometry Index. GPT-4.1 nano costs 171× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. Claude Opus 4 scores higher in 10 categories and GPT-4.1 nano in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Opus 4 leads 47.8 to 23.8.
- The biggest single-benchmark swing is Aider Polyglot: 72% for Claude Opus 4 and 8.9% for GPT-4.1 nano.
- GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Opus 4 | GPT-4.1 nano | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 42.9 | 27.7 |
| Released | 2025-05-22 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 32K | 33K |
| Input $ / M tokens | $15 | $0.10 |
| Output $ / M tokens | $75 | $0.40 |
| Results tracked | 56 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4 leads
Claude Opus 4: 47.8 (#55), GPT-4.1 nano: 23.8 (#325)
| Benchmark | Claude Opus 4 | GPT-4.1 nano |
|---|---|---|
| Aider Polyglot | 72% | 8.9% |
| WeirdML | 43.7% | 19% |
| LMArena Coding | 1442 | 1306 |
| SWE-bench Verified | 70.7% | — |
| SWE-bench Verified (bash only) | 67.6% | — |
| SciCode | — | 25.9% |
| GSO | 6.9% | — |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Claude Opus 4 leads
Claude Opus 4: 34.5 (#39), GPT-4.1 nano: 26.3 (#98)
| Benchmark | Claude Opus 4 | GPT-4.1 nano |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 33% |
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
Reasoning Claude Opus 4 leads
Claude Opus 4: 27.4 (#104), GPT-4.1 nano: 8.6 (#344)
| Benchmark | Claude Opus 4 | GPT-4.1 nano |
|---|---|---|
| ARC-AGI-2 | 8.6% | 0% |
| Kagi LLM Benchmark | 74.3% | 33.3% |
| ARC-AGI-1 | 35.7% | 0% |
| CritPt | 0.3% | 0% |
| LMArena Hard Prompts | 1399 | 1286 |
| DTBench | 81.6% | 52.5% |
| LMCA | 37.4% | 5.5% |
| Epoch Capabilities Index | 142.67 | 129.62 |
| SimpleBench | 58.8% | — |
| EnigmaEval | 5.6% | — |
| ForecastBench | 61.1 | — |
Math Claude Opus 4 leads
Claude Opus 4: 40.2 (#80), GPT-4.1 nano: 25.5 (#246)
| Benchmark | Claude Opus 4 | GPT-4.1 nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 28.9% |
| Omni-MATH | 61.6% | 36.7% |
| LMArena Math | 1391 | 1274 |
| MATH Level 5 | 85% | 70% |
| FrontierMath (Feb 2025 set) | 4.5% | 1% |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 4 leads
Claude Opus 4: 43.9 (#82), GPT-4.1 nano: 21.8 (#268)
| Benchmark | Claude Opus 4 | GPT-4.1 nano |
|---|---|---|
| GPQA Diamond | 76.3% | 48.9% |
| MMLU-Pro | 87.5% | 55% |
| GPQA (HELM) | 70.8% | 50.7% |
| LMArena Expert | 1384 | 1272 |
| Humanity's Last Exam | 10.7% | — |
| SimpleQA Verified | — | 6% |
| Confabulations | 15.9% | — |
| Vectara Hallucination Rate | 12% | — |
Multimodal Claude Opus 4 leads
Claude Opus 4: 30.9 (#101), GPT-4.1 nano: 28.6 (#108)
| Benchmark | Claude Opus 4 | GPT-4.1 nano |
|---|---|---|
| LMArena Vision | 1192 | 1063 |
| GeoBench | 49% | — |
| VPCT | 38% | — |
Multilingual Claude Opus 4 leads
Claude Opus 4: 49.0 (#133), GPT-4.1 nano: 41.8 (#200)
| Benchmark | Claude Opus 4 | GPT-4.1 nano |
|---|---|---|
| LMArena Non-English | 1362 | 1260 |
| LMArena Chinese | 1386 | 1270 |
| LMArena German | 1391 | 1288 |
| LMArena Japanese | 1332 | 1199 |
| LMArena Russian | 1392 | 1261 |
| LMArena French | 1370 | — |
| LMArena Korean | 1318 | — |
| LMArena Spanish | 1388 | — |
Instruction Following Claude Opus 4 leads
Claude Opus 4: 77.3 (#26), GPT-4.1 nano: 68.0 (#188)
| Benchmark | Claude Opus 4 | GPT-4.1 nano |
|---|---|---|
| IFEval | 91.8% | 84.3% |
| LMArena Instruction Following | 1406 | 1267 |
Long Context Claude Opus 4 leads
Claude Opus 4: 39.5 (#167), GPT-4.1 nano: 23.7 (#291)
| Benchmark | Claude Opus 4 | GPT-4.1 nano |
|---|---|---|
| Fiction.LiveBench | 61.1% | 25% |
| LMArena Longer Query | 1422 | 1283 |
Writing & Preference Claude Opus 4 leads
Claude Opus 4: 61.4 (#85), GPT-4.1 nano: 40.7 (#238)
| Benchmark | Claude Opus 4 | GPT-4.1 nano |
|---|---|---|
| LMArena Text | 1377 | 1285 |
| LMArena Creative Writing | 1386 | 1260 |
| EQ-Bench Creative Writing | 1580 | 946 |
| WildBench | 85.2% | 81.2% |
| LMArena Multi-Turn | 1396 | 1277 |
| Short-Story Creative Writing | 83.6% | — |
Frequently asked questions
Is Claude Opus 4 better than GPT-4.1 nano?
Claude Opus 4 is the stronger model overall, scoring 42.9 to 27.7 on the Noometry Index. GPT-4.1 nano costs 171× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4 or GPT-4.1 nano?
GPT-4.1 nano is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or GPT-4.1 nano better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.8 versus 23.8 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 nano does, with 1.05M tokens against 200K.
How many benchmarks do Claude Opus 4 and GPT-4.1 nano share?
35 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and GPT-4.1 nano has 38.