Model comparison
GPT-4.1 mini vs GPT-5 Nano
GPT-4.1 mini and GPT-5 Nano score almost the same on the Noometry Index (33.6 vs 33.5), so choose on price, context window or the category you care about most.
Last verified . 41 shared benchmarks.
Summary
- They share 41 benchmarks with published results for both. GPT-4.1 mini scores higher in 5 categories and GPT-5 Nano in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4.1 mini leads 48.6 to 39.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 44.7% for GPT-4.1 mini and 81.1% for GPT-5 Nano.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $0.40 / $1.60 for GPT-4.1 mini.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-4.1 mini | GPT-5 Nano | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 33.6 | 33.5 |
| Released | 2025-04-14 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 33K | 128K |
| Input $ / M tokens | $0.40 | $0.05 |
| Output $ / M tokens | $1.60 | $0.40 |
| Results tracked | 47 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Nano leads
GPT-4.1 mini: 30.6 (#293), GPT-5 Nano: 33.6 (#254)
| Benchmark | GPT-4.1 mini | GPT-5 Nano |
|---|---|---|
| SWE-bench Verified (bash only) | 23.9% | 34.8% |
| WeirdML | 37.6% | 38.1% |
| LMArena Coding | 1367 | 1351 |
| Aider Polyglot | 32.4% | — |
| SciCode | 40.4% | — |
| BigCodeBench Instruct | 48.9% | — |
| CadEval | 16% | — |
| ALE-Bench | — | 718.67 |
Agentic & Tool Use GPT-4.1 mini leads
GPT-4.1 mini: 33.3 (#55), GPT-5 Nano: 25.8 (#106)
| Benchmark | GPT-4.1 mini | GPT-5 Nano |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | 51.5% |
| Terminal-Bench | — | 21.8% |
Reasoning GPT-5 Nano leads
GPT-4.1 mini: 10.8 (#340), GPT-5 Nano: 16.3 (#306)
| Benchmark | GPT-4.1 mini | GPT-5 Nano |
|---|---|---|
| ARC-AGI-2 | 0% | 2.6% |
| Kagi LLM Benchmark | 48.6% | 62.2% |
| ARC-AGI-1 | 3.5% | 20.7% |
| Chess Puzzles | 7% | 27% |
| LMArena Hard Prompts | 1349 | 1328 |
| Mystery Game Puzzles | 7% | 9% |
| DTBench | 68.8% | 62.7% |
| LMCA | 21.1% | 7.9% |
| Epoch Capabilities Index | 135.01 | 139.38 |
| CritPt | 0% | — |
| ForecastBench | — | 59.1 |
Math GPT-5 Nano leads
GPT-4.1 mini: 24.1 (#270), GPT-5 Nano: 29.4 (#241)
| Benchmark | GPT-4.1 mini | GPT-5 Nano |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6.7% | 20% |
| OTIS Mock AIME 2024-2025 | 44.7% | 81.1% |
| Omni-MATH | 49.1% | 54.6% |
| LMArena Math | 1343 | 1317 |
| MATH Level 5 | 87.3% | 95.2% |
| FrontierMath (Feb 2025 set) | 4.5% | 8.3% |
| FrontierMath Tier 4 | — | 2.4% |
| ProofBench | — | 12% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GPT-5 Nano leads
GPT-4.1 mini: 34.7 (#194), GPT-5 Nano: 35.9 (#178)
| Benchmark | GPT-4.1 mini | GPT-5 Nano |
|---|---|---|
| GPQA Diamond | 65.8% | 69.4% |
| SimpleQA Verified | 12.7% | 11.7% |
| MMLU-Pro | 78.3% | 77.8% |
| GPQA (HELM) | 61.4% | 67.9% |
| LMArena Expert | 1338 | 1321 |
| Vectara Hallucination Rate | — | 10.5% |
Multimodal GPT-4.1 mini leads
GPT-4.1 mini: 35.8 (#82), GPT-5 Nano: 31.3 (#108)
| Benchmark | GPT-4.1 mini | GPT-5 Nano |
|---|---|---|
| LMArena Vision | 1181 | 1159 |
| VPCT | — | 37.2% |
Multilingual Too close to call
GPT-4.1 mini: 45.7 (#166), GPT-5 Nano: 45.3 (#172)
| Benchmark | GPT-4.1 mini | GPT-5 Nano |
|---|---|---|
| LMArena Non-English | 1318 | 1313 |
| LMArena Chinese | 1329 | 1356 |
| LMArena German | 1351 | 1327 |
| LMArena Japanese | 1290 | 1226 |
| LMArena Korean | 1298 | 1269 |
| LMArena Russian | 1324 | 1296 |
| LMArena Spanish | 1319 | 1360 |
| LMArena French | 1358 | — |
Instruction Following GPT-5 Nano leads
GPT-4.1 mini: 73.7 (#118), GPT-5 Nano: 75.0 (#79)
| Benchmark | GPT-4.1 mini | GPT-5 Nano |
|---|---|---|
| IFEval | 90.4% | 93.2% |
| LMArena Instruction Following | 1333 | 1306 |
Long Context Too close to call
GPT-4.1 mini: 31.8 (#275), GPT-5 Nano: 31.3 (#281)
| Benchmark | GPT-4.1 mini | GPT-5 Nano |
|---|---|---|
| Fiction.LiveBench | 44.4% | 44.4% |
| LMArena Longer Query | 1344 | 1312 |
Writing & Preference GPT-4.1 mini leads
GPT-4.1 mini: 48.6 (#199), GPT-5 Nano: 39.1 (#249)
| Benchmark | GPT-4.1 mini | GPT-5 Nano |
|---|---|---|
| LMArena Text | 1340 | 1320 |
| LMArena Creative Writing | 1300 | 1249 |
| EQ-Bench Creative Writing | 1147 | 705 |
| WildBench | 83.8% | 80.6% |
| LMArena Multi-Turn | 1354 | 1311 |
Frequently asked questions
Is GPT-4.1 mini better than GPT-5 Nano?
GPT-4.1 mini and GPT-5 Nano score almost the same on the Noometry Index (33.6 vs 33.5), so choose on price, context window or the category you care about most.
Which is cheaper, GPT-4.1 mini 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-4.1 mini lists at $0.40 and $1.60.
Is GPT-4.1 mini or GPT-5 Nano better for coding?
GPT-5 Nano scores higher on coding benchmarks: 33.6 versus 30.6 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 mini does, with 1.05M tokens against 400K.
How many benchmarks do GPT-4.1 mini and GPT-5 Nano share?
41 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and GPT-5 Nano has 49.