Model comparison
Claude Opus 5 vs GPT-4.1 nano
Claude Opus 5 is the stronger model overall, scoring 67.8 to 27.9 on the Noometry Index. GPT-4.1 nano costs 57× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Claude Opus 5 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 reasoning, where Claude Opus 5 leads 77.2 to 8.5.
- The biggest single-benchmark swing is ARC-AGI-1: 97.5% for Claude Opus 5 and 0% for GPT-4.1 nano.
- GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $5 / $25 for Claude Opus 5.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Opus 5 | GPT-4.1 nano | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 67.8 | 27.9 |
| Released | 2026-07-24 | 2025-04-14 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 33K |
| Input $ / M tokens | $5 | $0.10 |
| Output $ / M tokens | $25 | $0.40 |
| Results tracked | 57 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5 leads
Claude Opus 5: 67.5 (#5), GPT-4.1 nano: 24.1 (#330)
| Benchmark | Claude Opus 5 | GPT-4.1 nano |
|---|---|---|
| SciCode | 56.4% | 25.9% |
| WeirdML | 91.8% | 19% |
| LMArena Coding | 1534 | 1306 |
| DeepSWE | 73.6% | — |
| FrontierCode | 53.4% | — |
| Aider Polyglot | — | 8.9% |
| CursorBench | 46.6% | — |
| LMArena WebDev | 1691 | — |
| FrontierSWE | 52% | — |
| ALE-Bench | 2,165 | — |
Agentic & Tool Use Claude Opus 5 leads
Claude Opus 5: 55.6 (#1), GPT-4.1 nano: 26.5 (#104)
| Benchmark | Claude Opus 5 | GPT-4.1 nano |
|---|---|---|
| APEX-Agents | 65.8% | — |
| Berkeley Function Calling Leaderboard | — | 33% |
| OSWorld 2.0 | 31.4% | — |
| τ²-bench Banking | 48.7% | — |
| PostTrainBench | 35% | — |
| BALROG | 63.4% | — |
| GBAEval | 79.6% | — |
| GDP.pdf | 24% | — |
| Vending-Bench 2 | 11,182 | — |
Reasoning Claude Opus 5 leads
Claude Opus 5: 77.2 (#4), GPT-4.1 nano: 8.5 (#349)
| Benchmark | Claude Opus 5 | GPT-4.1 nano |
|---|---|---|
| ARC-AGI-2 | 90.4% | 0% |
| ARC-AGI-1 | 97.5% | 0% |
| CritPt | 29.1% | 0% |
| LMArena Hard Prompts | 1526 | 1286 |
| DTBench | 97.9% | 52.5% |
| LMCA | 64.5% | 5.5% |
| Epoch Capabilities Index | 162.78 | 129.62 |
| SimpleBench | 80.6% | — |
| Kagi LLM Benchmark | — | 33.3% |
| NYT Connections (extended) | 94.3% | — |
| Chess Puzzles | 42% | — |
| EBR-Bench | 45.7% | — |
| Mystery Game Puzzles | 59% | — |
| Bench to the Future 3 | 0.12 | — |
Math Claude Opus 5 leads
Claude Opus 5: 86.2 (#8), GPT-4.1 nano: 26.9 (#252)
| Benchmark | Claude Opus 5 | GPT-4.1 nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.9% | 28.9% |
| LMArena Math | 1531 | 1274 |
| FrontierMath (Tiers 1-3) | 85.6% | — |
| FrontierMath Tier 4 | 73.2% | — |
| ProofBench | 99% | — |
| Omni-MATH | — | 36.7% |
| MATH Level 5 | — | 70% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Claude Opus 5 leads
Claude Opus 5: 66.8 (#9), GPT-4.1 nano: 21.8 (#273)
| Benchmark | Claude Opus 5 | GPT-4.1 nano |
|---|---|---|
| GPQA Diamond | 93.9% | 48.9% |
| SimpleQA Verified | 59.9% | 6% |
| LMArena Expert | 1557 | 1272 |
| MMLU-Pro | — | 55% |
| GPQA (HELM) | — | 50.7% |
Multimodal Claude Opus 5 leads
Claude Opus 5: 50.8 (#8), GPT-4.1 nano: 29.2 (#113)
| Benchmark | Claude Opus 5 | GPT-4.1 nano |
|---|---|---|
| LMArena Vision | 1319 | 1063 |
| Blueprint-Bench 2 | 30.4% | — |
| Furniture Assembly | 60.8% | — |
| LMArena Document | 1516 | — |
Multilingual Claude Opus 5 leads
Claude Opus 5: 58.8 (#4), GPT-4.1 nano: 41.6 (#205)
| Benchmark | Claude Opus 5 | GPT-4.1 nano |
|---|---|---|
| LMArena Non-English | 1501 | 1260 |
| LMArena Chinese | 1574 | 1270 |
| LMArena German | 1524 | 1288 |
| LMArena Japanese | 1516 | 1198 |
| LMArena Russian | 1507 | 1261 |
| LMArena French | 1519 | — |
| LMArena Korean | 1521 | — |
| LMArena Spanish | 1519 | — |
Instruction Following Claude Opus 5 leads
Claude Opus 5: 79.2 (#7), GPT-4.1 nano: 67.8 (#193)
| Benchmark | Claude Opus 5 | GPT-4.1 nano |
|---|---|---|
| LMArena Instruction Following | 1517 | 1267 |
| IFEval | — | 84.3% |
Long Context Claude Opus 5 leads
Claude Opus 5: 46.5 (#21), GPT-4.1 nano: 23.7 (#296)
| Benchmark | Claude Opus 5 | GPT-4.1 nano |
|---|---|---|
| LMArena Longer Query | 1515 | 1283 |
| Fiction.LiveBench | — | 25% |
Writing & Preference Claude Opus 5 leads
Claude Opus 5: 79.2 (#1), GPT-4.1 nano: 40.5 (#243)
| Benchmark | Claude Opus 5 | GPT-4.1 nano |
|---|---|---|
| LMArena Text | 1507 | 1285 |
| LMArena Creative Writing | 1491 | 1260 |
| EQ-Bench Creative Writing | 2133 | 946 |
| LMArena Multi-Turn | 1499 | 1277 |
| WildBench | — | 81.2% |
| EQ-Bench 4 | 1385 | — |
Frequently asked questions
Is Claude Opus 5 better than GPT-4.1 nano?
Claude Opus 5 is the stronger model overall, scoring 67.8 to 27.9 on the Noometry Index. GPT-4.1 nano costs 57× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 5 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 5 lists at $5 and $25.
Is Claude Opus 5 or GPT-4.1 nano better for coding?
Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 24.1 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 nano does, with 1.05M tokens against 1M.
How many benchmarks do Claude Opus 5 and GPT-4.1 nano share?
27 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and GPT-4.1 nano has 38.