Model comparison
GPT-4.1 nano vs GPT-5 Mini
GPT-5 Mini is the stronger model overall, scoring 41.7 to 27.7 on the Noometry Index. GPT-4.1 nano costs 3.9× less per token, which makes it the better buy when GPT-5 Mini's lead doesn't matter for your workload.
Last verified . 37 shared benchmarks.
Summary
- They share 37 benchmarks with published results for both. GPT-4.1 nano scores higher in 0 categories and GPT-5 Mini in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5 Mini leads 45.5 to 21.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 28.9% for GPT-4.1 nano and 86.7% for GPT-5 Mini.
- GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.25 / $2 for GPT-5 Mini.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-4.1 nano | GPT-5 Mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 27.7 | 41.7 |
| Released | 2025-04-14 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 33K | 128K |
| Input $ / M tokens | $0.10 | $0.25 |
| Output $ / M tokens | $0.40 | $2 |
| Results tracked | 38 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Mini leads
GPT-4.1 nano: 23.8 (#325), GPT-5 Mini: 40.0 (#134)
| Benchmark | GPT-4.1 nano | GPT-5 Mini |
|---|---|---|
| SciCode | 25.9% | 39.2% |
| WeirdML | 19% | 52.7% |
| LMArena Coding | 1306 | 1406 |
| SWE-bench Verified | — | 64.7% |
| SWE-bench Verified (bash only) | — | 59.8% |
| Aider Polyglot | 8.9% | — |
| SWE-bench Multilingual | — | 39.7% |
| ALE-Bench | — | 799.77 |
| AlgoTune | — | 1.38 |
Agentic & Tool Use GPT-5 Mini leads
GPT-4.1 nano: 26.3 (#98), GPT-5 Mini: 31.0 (#64)
| Benchmark | GPT-4.1 nano | GPT-5 Mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 33% | 55.5% |
| Terminal-Bench | — | 34.8% |
| Vending-Bench 2 | — | -31.18 |
Reasoning GPT-5 Mini leads
GPT-4.1 nano: 8.6 (#344), GPT-5 Mini: 24.1 (#153)
| Benchmark | GPT-4.1 nano | GPT-5 Mini |
|---|---|---|
| ARC-AGI-2 | 0% | 4.4% |
| Kagi LLM Benchmark | 33.3% | 70.3% |
| ARC-AGI-1 | 0% | 54.3% |
| CritPt | 0% | 0% |
| LMArena Hard Prompts | 1286 | 1380 |
| DTBench | 52.5% | 80.5% |
| LMCA | 5.5% | 34.2% |
| Epoch Capabilities Index | 129.62 | 145.51 |
| Chess Puzzles | — | 30% |
| EnigmaEval | — | 8.2% |
| Mystery Game Puzzles | — | 10% |
| ForecastBench | — | 61 |
Math GPT-5 Mini leads
GPT-4.1 nano: 25.5 (#246), GPT-5 Mini: 46.3 (#59)
| Benchmark | GPT-4.1 nano | GPT-5 Mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 28.9% | 86.7% |
| Omni-MATH | 36.7% | 72.2% |
| LMArena Math | 1274 | 1377 |
| MATH Level 5 | 70% | 97.8% |
| FrontierMath (Feb 2025 set) | 1% | 27.2% |
| FrontierMath (Tiers 1-3) | — | 46.7% |
| FrontierMath Tier 4 | — | 12.2% |
| ProofBench | — | 9% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge GPT-5 Mini leads
GPT-4.1 nano: 21.8 (#268), GPT-5 Mini: 45.5 (#80)
| Benchmark | GPT-4.1 nano | GPT-5 Mini |
|---|---|---|
| GPQA Diamond | 48.9% | 75% |
| SimpleQA Verified | 6% | 21.6% |
| MMLU-Pro | 55% | 83.5% |
| GPQA (HELM) | 50.7% | 75.6% |
| LMArena Expert | 1272 | 1377 |
| Humanity's Last Exam | — | 19.4% |
| Confabulations | — | 13.3% |
| Vectara Hallucination Rate | — | 12.9% |
Multimodal GPT-5 Mini leads
GPT-4.1 nano: 28.6 (#108), GPT-5 Mini: 35.0 (#80)
| Benchmark | GPT-4.1 nano | GPT-5 Mini |
|---|---|---|
| LMArena Vision | 1063 | 1202 |
| VPCT | — | 40.2% |
Multilingual GPT-5 Mini leads
GPT-4.1 nano: 41.8 (#200), GPT-5 Mini: 49.1 (#131)
| Benchmark | GPT-4.1 nano | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1260 | 1363 |
| LMArena Chinese | 1270 | 1387 |
| LMArena German | 1288 | 1366 |
| LMArena Japanese | 1199 | 1342 |
| LMArena Russian | 1261 | 1362 |
| LMArena French | — | 1385 |
| LMArena Korean | — | 1306 |
| LMArena Spanish | — | 1355 |
Instruction Following GPT-5 Mini leads
GPT-4.1 nano: 68.0 (#188), GPT-5 Mini: 76.4 (#43)
| Benchmark | GPT-4.1 nano | GPT-5 Mini |
|---|---|---|
| IFEval | 84.3% | 92.7% |
| LMArena Instruction Following | 1267 | 1357 |
Long Context GPT-5 Mini leads
GPT-4.1 nano: 23.7 (#291), GPT-5 Mini: 41.9 (#127)
| Benchmark | GPT-4.1 nano | GPT-5 Mini |
|---|---|---|
| Fiction.LiveBench | 25% | 69.4% |
| LMArena Longer Query | 1283 | 1355 |
Writing & Preference GPT-5 Mini leads
GPT-4.1 nano: 40.7 (#238), GPT-5 Mini: 55.4 (#143)
| Benchmark | GPT-4.1 nano | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1285 | 1373 |
| LMArena Creative Writing | 1260 | 1325 |
| EQ-Bench Creative Writing | 946 | 1313 |
| WildBench | 81.2% | 85.5% |
| LMArena Multi-Turn | 1277 | 1363 |
| Short-Story Creative Writing | — | 83.1% |
Frequently asked questions
Is GPT-4.1 nano better than GPT-5 Mini?
GPT-5 Mini is the stronger model overall, scoring 41.7 to 27.7 on the Noometry Index. GPT-4.1 nano costs 3.9× less per token, which makes it the better buy when GPT-5 Mini's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 nano or GPT-5 Mini?
GPT-4.1 nano is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; GPT-5 Mini lists at $0.25 and $2.
Is GPT-4.1 nano or GPT-5 Mini better for coding?
GPT-5 Mini scores higher on coding benchmarks: 40.0 versus 23.8 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 nano does, with 1.05M tokens against 400K.
How many benchmarks do GPT-4.1 nano and GPT-5 Mini share?
37 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and GPT-5 Mini has 60.