Model comparison
GPT-5.1 vs GPT-5 Nano
GPT-5.1 is the stronger model overall, scoring 49.0 to 33.5 on the Noometry Index. GPT-5 Nano costs 25× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Last verified . 41 shared benchmarks.
Summary
- They share 41 benchmarks with published results for both. GPT-5.1 scores higher in 10 categories and GPT-5 Nano in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-5.1 leads 64.5 to 39.1.
- The biggest single-benchmark swing is ARC-AGI-1: 72.8% for GPT-5.1 and 20.7% for GPT-5 Nano.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
Side by side
| GPT-5.1 | GPT-5 Nano | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 49.0 | 33.5 |
| Released | 2025-11-13 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 400K |
| Max output | 128K | 128K |
| Input $ / M tokens | $1.25 | $0.05 |
| Output $ / M tokens | $10 | $0.40 |
| Results tracked | 63 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
GPT-5.1: 46.4 (#66), GPT-5 Nano: 33.6 (#254)
| Benchmark | GPT-5.1 | GPT-5 Nano |
|---|---|---|
| SWE-bench Verified (bash only) | 66% | 34.8% |
| WeirdML | 60.8% | 38.1% |
| LMArena Coding | 1454 | 1351 |
| ALE-Bench | 1,192 | 718.67 |
| SWE-bench Verified | 68% | — |
| LMArena WebDev | 1395 | — |
| SciCode | 43.3% | — |
| GSO | 13.7% | — |
| LiveBench Coding | 72.5% | — |
Agentic & Tool Use GPT-5.1 leads
GPT-5.1: 32.7 (#60), GPT-5 Nano: 25.8 (#106)
| Benchmark | GPT-5.1 | GPT-5 Nano |
|---|---|---|
| Terminal-Bench | 47.6% | 21.8% |
| Berkeley Function Calling Leaderboard | — | 51.5% |
| DeepResearch Bench | 42.8% | — |
| LMArena Search | 1199 | — |
| Vending-Bench 2 | 1,473 | — |
Reasoning GPT-5.1 leads
GPT-5.1: 39.8 (#58), GPT-5 Nano: 16.3 (#306)
| Benchmark | GPT-5.1 | GPT-5 Nano |
|---|---|---|
| ARC-AGI-2 | 17.6% | 2.6% |
| ARC-AGI-1 | 72.8% | 20.7% |
| Chess Puzzles | 32% | 27% |
| LMArena Hard Prompts | 1457 | 1328 |
| Mystery Game Puzzles | 19% | 9% |
| DTBench | 90.1% | 62.7% |
| LMCA | 43.9% | 7.9% |
| Epoch Capabilities Index | 149.64 | 139.38 |
| ForecastBench | 58.1 | 59.1 |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | — | 62.2% |
| CritPt | 4.9% | — |
| EnigmaEval | 11.2% | — |
| LiveBench Reasoning | 95.8% | — |
| LiveBench Data Analysis | 72.1% | — |
| LiveBench | 78.8% | — |
Math GPT-5.1 leads
GPT-5.1: 52.2 (#51), GPT-5 Nano: 29.4 (#241)
| Benchmark | GPT-5.1 | GPT-5 Nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.6% | 81.1% |
| Omni-MATH | 46.4% | 54.6% |
| LMArena Math | 1447 | 1317 |
| FrontierMath (Feb 2025 set) | 31% | 8.3% |
| FrontierMath Tier 4 (v1) | 12.5% | 2.1% |
| FrontierMath (Tiers 1-3) | — | 20% |
| FrontierMath Tier 4 | — | 2.4% |
| ProofBench | — | 12% |
| LiveBench Math | 94.5% | — |
| MATH Level 5 | — | 95.2% |
Knowledge GPT-5.1 leads
GPT-5.1: 50.6 (#71), GPT-5 Nano: 35.9 (#178)
| Benchmark | GPT-5.1 | GPT-5 Nano |
|---|---|---|
| GPQA Diamond | 87.6% | 69.4% |
| SimpleQA Verified | 48% | 11.7% |
| MMLU-Pro | 57.9% | 77.8% |
| Vectara Hallucination Rate | 10.9% | 10.5% |
| GPQA (HELM) | 44.2% | 67.9% |
| LMArena Expert | 1470 | 1321 |
| Humanity's Last Exam | 23.7% | — |
Multimodal GPT-5.1 leads
GPT-5.1: 44.8 (#19), GPT-5 Nano: 31.3 (#108)
| Benchmark | GPT-5.1 | GPT-5 Nano |
|---|---|---|
| LMArena Vision | 1250 | 1159 |
| VPCT | 58.7% | 37.2% |
| LMArena Document | 1403 | — |
Multilingual GPT-5.1 leads
GPT-5.1: 53.8 (#56), GPT-5 Nano: 45.3 (#172)
| Benchmark | GPT-5.1 | GPT-5 Nano |
|---|---|---|
| LMArena Non-English | 1431 | 1313 |
| LMArena Chinese | 1495 | 1356 |
| LMArena German | 1438 | 1327 |
| LMArena Japanese | 1453 | 1226 |
| LMArena Korean | 1401 | 1269 |
| LMArena Russian | 1435 | 1296 |
| LMArena Spanish | 1433 | 1360 |
| LMArena French | 1450 | — |
Instruction Following GPT-5.1 leads
GPT-5.1: 83.9 (#1), GPT-5 Nano: 75.0 (#79)
| Benchmark | GPT-5.1 | GPT-5 Nano |
|---|---|---|
| IFEval | 93.5% | 93.2% |
| LMArena Instruction Following | 1443 | 1306 |
| LiveBench Instruction Following | 93.3% | — |
Long Context GPT-5.1 leads
GPT-5.1: 47.6 (#14), GPT-5 Nano: 31.3 (#281)
| Benchmark | GPT-5.1 | GPT-5 Nano |
|---|---|---|
| LMArena Longer Query | 1447 | 1312 |
| Fiction.LiveBench | — | 44.4% |
| CL-bench | 23.7% | — |
| CL-bench Life | 17.3% | — |
Writing & Preference GPT-5.1 leads
GPT-5.1: 64.5 (#55), GPT-5 Nano: 39.1 (#249)
| Benchmark | GPT-5.1 | GPT-5 Nano |
|---|---|---|
| LMArena Text | 1443 | 1320 |
| LMArena Creative Writing | 1427 | 1249 |
| WildBench | 86.3% | 80.6% |
| LMArena Multi-Turn | 1450 | 1311 |
| EQ-Bench Creative Writing | — | 705 |
| LiveBench Language | 80.2% | — |
Frequently asked questions
Is GPT-5.1 better than GPT-5 Nano?
GPT-5.1 is the stronger model overall, scoring 49.0 to 33.5 on the Noometry Index. GPT-5 Nano costs 25× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Which is cheaper, GPT-5.1 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; GPT-5.1 lists at $1.25 and $10.
Is GPT-5.1 or GPT-5 Nano better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.4 versus 33.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 400K tokens.
How many benchmarks do GPT-5.1 and GPT-5 Nano share?
41 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and GPT-5 Nano has 49.