Model comparison
GPT-4.1 vs GPT-5.4 nano
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 35.9 on the Noometry Index.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. GPT-4.1 scores higher in 3 categories and GPT-5.4 nano in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 nano leads 40.9 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 38.3% for GPT-4.1 and 87.8% for GPT-5.4 nano.
- GPT-5.4 nano is cheaper at $0.20 / $1.25 per million input/output tokens, against $2 / $8 for GPT-4.1.
- GPT-4.1 accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-4.1 | GPT-5.4 nano | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 35.9 | 41.9 |
| Released | 2025-04-14 | 2026-03-17 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 33K | 128K |
| Input $ / M tokens | $2 | $0.20 |
| Output $ / M tokens | $8 | $1.25 |
| Results tracked | 52 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 nano leads
GPT-4.1: 34.4 (#238), GPT-5.4 nano: 43.6 (#84)
| Benchmark | GPT-4.1 | GPT-5.4 nano |
|---|---|---|
| WeirdML | 39% | 49.2% |
| LMArena Coding | 1391 | 1405 |
| ALE-Bench | 558.1 | 1,005 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| SciCode | — | 46.9% |
| CadEval | 42% | — |
Agentic & Tool Use Not comparable
GPT-4.1: 34.7 (#43), GPT-5.4 nano: —
| Benchmark | GPT-4.1 | GPT-5.4 nano |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
Reasoning GPT-5.4 nano leads
GPT-4.1: 11.7 (#339), GPT-5.4 nano: 23.7 (#173)
| Benchmark | GPT-4.1 | GPT-5.4 nano |
|---|---|---|
| ARC-AGI-2 | 0.4% | 5.7% |
| Kagi LLM Benchmark | 52.3% | 39.7% |
| ARC-AGI-1 | 5.5% | 51.5% |
| Chess Puzzles | 6% | 30% |
| LMArena Hard Prompts | 1384 | 1381 |
| DTBench | 68.3% | 80.3% |
| LMCA | 25.6% | 36.9% |
| Epoch Capabilities Index | 136.78 | 145.81 |
| ForecastBench | 61.5 | 57.3 |
| SimpleBench | 27% | — |
| CritPt | — | 9.3% |
| EnigmaEval | 2.2% | — |
| Mystery Game Puzzles | — | 9% |
Math GPT-5.4 nano leads
GPT-4.1: 22.3 (#280), GPT-5.4 nano: 40.9 (#88)
| Benchmark | GPT-4.1 | GPT-5.4 nano |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6% | 44.9% |
| OTIS Mock AIME 2024-2025 | 38.3% | 87.8% |
| LMArena Math | 1370 | 1406 |
| FrontierMath (Feb 2025 set) | 5.5% | 25.9% |
| FrontierMath Tier 4 (v1) | 0% | 6.3% |
| FrontierMath Tier 4 | — | 12.2% |
| ProofBench | — | 5% |
| Omni-MATH | 47.1% | — |
| MATH Level 5 | 83% | — |
Knowledge GPT-5.4 nano leads
GPT-4.1: 37.1 (#160), GPT-5.4 nano: 41.9 (#103)
| Benchmark | GPT-4.1 | GPT-5.4 nano |
|---|---|---|
| GPQA Diamond | 66.9% | 78.5% |
| SimpleQA Verified | 31.1% | 11.7% |
| Vectara Hallucination Rate | 5.6% | 3.1% |
| LMArena Expert | 1364 | 1396 |
| Humanity's Last Exam | 5.4% | — |
| MMLU-Pro | 81.1% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal GPT-4.1 leads
GPT-4.1: 38.2 (#67), GPT-5.4 nano: 36.7 (#78)
| Benchmark | GPT-4.1 | GPT-5.4 nano |
|---|---|---|
| LMArena Vision | 1211 | 1196 |
| GeoBench | 72% | — |
Multilingual Too close to call
GPT-4.1: 49.4 (#133), GPT-5.4 nano: 48.6 (#140)
| Benchmark | GPT-4.1 | GPT-5.4 nano |
|---|---|---|
| LMArena Non-English | 1370 | 1359 |
| LMArena Chinese | 1382 | 1392 |
| LMArena French | 1382 | 1396 |
| LMArena German | 1381 | 1367 |
| LMArena Japanese | 1319 | 1343 |
| LMArena Korean | 1339 | 1320 |
| LMArena Russian | 1377 | 1363 |
| LMArena Spanish | 1376 | 1371 |
Instruction Following Too close to call
GPT-4.1: 71.3 (#153), GPT-5.4 nano: 71.9 (#144)
| Benchmark | GPT-4.1 | GPT-5.4 nano |
|---|---|---|
| LMArena Instruction Following | 1367 | 1362 |
| IFEval | 83.8% | — |
Long Context GPT-5.4 nano leads
GPT-4.1: 40.0 (#163), GPT-5.4 nano: 41.6 (#137)
| Benchmark | GPT-4.1 | GPT-5.4 nano |
|---|---|---|
| LMArena Longer Query | 1385 | 1366 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference GPT-4.1 leads
GPT-4.1: 57.6 (#125), GPT-5.4 nano: 55.7 (#142)
| Benchmark | GPT-4.1 | GPT-5.4 nano |
|---|---|---|
| LMArena Text | 1383 | 1372 |
| LMArena Creative Writing | 1363 | 1314 |
| LMArena Multi-Turn | 1398 | 1382 |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is GPT-4.1 better than GPT-5.4 nano?
GPT-5.4 nano is the stronger model overall, scoring 41.9 to 35.9 on the Noometry Index.
Which is cheaper, GPT-4.1 or GPT-5.4 nano?
GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; GPT-4.1 lists at $2 and $8.
Is GPT-4.1 or GPT-5.4 nano better for coding?
GPT-5.4 nano scores higher on coding benchmarks: 43.6 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 does, with 1.05M tokens against 400K.
How many benchmarks do GPT-4.1 and GPT-5.4 nano share?
35 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and GPT-5.4 nano has 40.