Model comparison
Claude Opus 4.1 vs GPT-5 Nano
Claude Opus 4.1 is the stronger model overall, scoring 41.0 to 33.5 on the Noometry Index. GPT-5 Nano costs 218× less per token, which makes it the better buy when Claude Opus 4.1's lead doesn't matter for your workload.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. Claude Opus 4.1 scores higher in 8 categories and GPT-5 Nano in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Opus 4.1 leads 62.4 to 39.1.
- The biggest single-benchmark swing is LMCA: 37.1% for Claude Opus 4.1 and 7.9% for GPT-5 Nano.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- GPT-5 Nano accepts more context: 400K tokens versus 200K.
Side by side
| Claude Opus 4.1 | GPT-5 Nano | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 41.0 | 33.5 |
| Released | 2025-08-05 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 400K |
| Max output | 32K | 128K |
| Input $ / M tokens | $15 | $0.05 |
| Output $ / M tokens | $75 | $0.40 |
| Results tracked | 48 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.1 leads
Claude Opus 4.1: 44.4 (#73), GPT-5 Nano: 33.6 (#254)
| Benchmark | Claude Opus 4.1 | GPT-5 Nano |
|---|---|---|
| WeirdML | 45.9% | 38.1% |
| LMArena Coding | 1479 | 1351 |
| ALE-Bench | 674.77 | 718.67 |
| SWE-bench Verified | 73.3% | — |
| SWE-bench Verified (bash only) | — | 34.8% |
| LMArena WebDev | 1390 | — |
| AlgoTune | 1.34 | — |
Agentic & Tool Use Claude Opus 4.1 leads
Claude Opus 4.1: 35.0 (#41), GPT-5 Nano: 25.8 (#106)
| Benchmark | Claude Opus 4.1 | GPT-5 Nano |
|---|---|---|
| Terminal-Bench | 38% | 21.8% |
| Berkeley Function Calling Leaderboard | — | 51.5% |
| GDPval | 43.6% | — |
| Cybench | 42% | — |
| DeepResearch Bench | 48.3% | — |
| LMArena Search | 1148 | — |
| METR Time Horizons | 66.8% | — |
Reasoning Claude Opus 4.1 leads
Claude Opus 4.1: 32.2 (#76), GPT-5 Nano: 16.3 (#306)
| Benchmark | Claude Opus 4.1 | GPT-5 Nano |
|---|---|---|
| Chess Puzzles | 7% | 27% |
| LMArena Hard Prompts | 1443 | 1328 |
| Mystery Game Puzzles | 21% | 9% |
| DTBench | 80% | 62.7% |
| LMCA | 37.1% | 7.9% |
| Epoch Capabilities Index | 144.12 | 139.38 |
| ForecastBench | 62 | 59.1 |
| ARC-AGI-2 | — | 2.6% |
| SimpleBench | 60% | — |
| Kagi LLM Benchmark | — | 62.2% |
| ARC-AGI-1 | — | 20.7% |
| EnigmaEval | 7.2% | — |
| EBR-Bench | 7.9% | — |
Math GPT-5 Nano leads
Claude Opus 4.1: 22.3 (#277), GPT-5 Nano: 29.4 (#241)
| Benchmark | Claude Opus 4.1 | GPT-5 Nano |
|---|---|---|
| FrontierMath (Tiers 1-3) | 12.6% | 20% |
| FrontierMath Tier 4 | 2.4% | 2.4% |
| OTIS Mock AIME 2024-2025 | 68.9% | 81.1% |
| LMArena Math | 1431 | 1317 |
| FrontierMath (Feb 2025 set) | 7.2% | 8.3% |
| FrontierMath Tier 4 (v1) | 4.2% | 2.1% |
| ProofBench | — | 12% |
| Omni-MATH | — | 54.6% |
| MATH Level 5 | — | 95.2% |
Knowledge Claude Opus 4.1 leads
Claude Opus 4.1: 42.0 (#101), GPT-5 Nano: 35.9 (#178)
| Benchmark | Claude Opus 4.1 | GPT-5 Nano |
|---|---|---|
| GPQA Diamond | 77.3% | 69.4% |
| Vectara Hallucination Rate | 11.8% | 10.5% |
| LMArena Expert | 1439 | 1321 |
| Humanity's Last Exam | 11.5% | — |
| SimpleQA Verified | — | 11.7% |
| MMLU-Pro | — | 77.8% |
| Confabulations | 17.1% | — |
| GPQA (HELM) | — | 67.9% |
Multimodal GPT-5 Nano leads
Claude Opus 4.1: 26.8 (#119), GPT-5 Nano: 31.3 (#108)
| Benchmark | Claude Opus 4.1 | GPT-5 Nano |
|---|---|---|
| VPCT | 35% | 37.2% |
| LMArena Vision | — | 1159 |
Multilingual Claude Opus 4.1 leads
Claude Opus 4.1: 52.0 (#95), GPT-5 Nano: 45.3 (#172)
| Benchmark | Claude Opus 4.1 | GPT-5 Nano |
|---|---|---|
| LMArena Non-English | 1405 | 1313 |
| LMArena Chinese | 1427 | 1356 |
| LMArena German | 1413 | 1327 |
| LMArena Japanese | 1378 | 1226 |
| LMArena Korean | 1380 | 1269 |
| LMArena Russian | 1422 | 1296 |
| LMArena Spanish | 1448 | 1360 |
| LMArena French | 1431 | — |
Instruction Following Too close to call
Claude Opus 4.1: 75.6 (#58), GPT-5 Nano: 75.0 (#79)
| Benchmark | Claude Opus 4.1 | GPT-5 Nano |
|---|---|---|
| LMArena Instruction Following | 1435 | 1306 |
| IFEval | — | 93.2% |
Long Context Claude Opus 4.1 leads
Claude Opus 4.1: 44.5 (#63), GPT-5 Nano: 31.3 (#281)
| Benchmark | Claude Opus 4.1 | GPT-5 Nano |
|---|---|---|
| LMArena Longer Query | 1455 | 1312 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference Claude Opus 4.1 leads
Claude Opus 4.1: 62.4 (#74), GPT-5 Nano: 39.1 (#249)
| Benchmark | Claude Opus 4.1 | GPT-5 Nano |
|---|---|---|
| LMArena Text | 1419 | 1320 |
| LMArena Creative Writing | 1412 | 1249 |
| LMArena Multi-Turn | 1444 | 1311 |
| Short-Story Creative Writing | 84.7% | — |
| EQ-Bench Creative Writing | — | 705 |
| WildBench | — | 80.6% |
Frequently asked questions
Is Claude Opus 4.1 better than GPT-5 Nano?
Claude Opus 4.1 is the stronger model overall, scoring 41.0 to 33.5 on the Noometry Index. GPT-5 Nano costs 218× less per token, which makes it the better buy when Claude Opus 4.1's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4.1 or GPT-5 Nano?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Claude Opus 4.1 lists at $15 and $75.
Is Claude Opus 4.1 or GPT-5 Nano better for coding?
Claude Opus 4.1 scores higher on coding benchmarks: 44.4 versus 33.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Nano does, with 400K tokens against 200K.
How many benchmarks do Claude Opus 4.1 and GPT-5 Nano share?
33 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and GPT-5 Nano has 49.