Model comparison
GPT-5.4 nano vs GPT-5 Mini
GPT-5.4 nano and GPT-5 Mini score almost the same on the Noometry Index (41.9 vs 41.8), so choose on price, context window or the category you care about most.
Last verified . 40 shared benchmarks.
Summary
- They share 40 benchmarks with published results for both. GPT-5.4 nano scores higher in 3 categories and GPT-5 Mini in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Mini leads 46.7 to 40.9.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 39.7% for GPT-5.4 nano and 70.3% for GPT-5 Mini.
- GPT-5.4 nano is cheaper at $0.20 / $1.25 per million input/output tokens, against $0.25 / $2 for GPT-5 Mini.
Side by side
| GPT-5.4 nano | GPT-5 Mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 41.9 | 41.8 |
| Released | 2026-03-17 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 400K |
| Max output | 128K | 128K |
| Input $ / M tokens | $0.20 | $0.25 |
| Output $ / M tokens | $1.25 | $2 |
| Results tracked | 40 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 nano leads
GPT-5.4 nano: 43.6 (#84), GPT-5 Mini: 40.1 (#146)
| Benchmark | GPT-5.4 nano | GPT-5 Mini |
|---|---|---|
| SciCode | 46.9% | 39.2% |
| WeirdML | 49.2% | 52.7% |
| LMArena Coding | 1405 | 1406 |
| ALE-Bench | 1,005 | 799.77 |
| SWE-bench Verified | — | 64.7% |
| SWE-bench Verified (bash only) | — | 59.8% |
| SWE-bench Multilingual | — | 39.7% |
| AlgoTune | — | 1.38 |
Agentic & Tool Use Not comparable
GPT-5.4 nano: —, GPT-5 Mini: 31.1 (#70)
| Benchmark | GPT-5.4 nano | GPT-5 Mini |
|---|---|---|
| Terminal-Bench | — | 34.8% |
| Berkeley Function Calling Leaderboard | — | 55.5% |
| Vending-Bench 2 | — | -31.18 |
Reasoning Too close to call
GPT-5.4 nano: 23.7 (#173), GPT-5 Mini: 23.9 (#168)
| Benchmark | GPT-5.4 nano | GPT-5 Mini |
|---|---|---|
| ARC-AGI-2 | 5.7% | 4.4% |
| Kagi LLM Benchmark | 39.7% | 70.3% |
| ARC-AGI-1 | 51.5% | 54.3% |
| CritPt | 9.3% | 0% |
| Chess Puzzles | 30% | 30% |
| LMArena Hard Prompts | 1381 | 1380 |
| Mystery Game Puzzles | 9% | 10% |
| DTBench | 80.3% | 80.5% |
| LMCA | 36.9% | 34.2% |
| Epoch Capabilities Index | 145.81 | 145.52 |
| ForecastBench | 57.3 | 61 |
| EnigmaEval | — | 8.2% |
Math GPT-5 Mini leads
GPT-5.4 nano: 40.9 (#88), GPT-5 Mini: 46.7 (#69)
| Benchmark | GPT-5.4 nano | GPT-5 Mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 44.9% | 46.7% |
| FrontierMath Tier 4 | 12.2% | 12.2% |
| OTIS Mock AIME 2024-2025 | 87.8% | 86.7% |
| ProofBench | 5% | 9% |
| LMArena Math | 1406 | 1378 |
| FrontierMath (Feb 2025 set) | 25.9% | 27.2% |
| FrontierMath Tier 4 (v1) | 6.3% | 6.3% |
| Omni-MATH | — | 72.2% |
| MATH Level 5 | — | 97.8% |
Knowledge GPT-5 Mini leads
GPT-5.4 nano: 41.9 (#103), GPT-5 Mini: 45.6 (#86)
| Benchmark | GPT-5.4 nano | GPT-5 Mini |
|---|---|---|
| GPQA Diamond | 78.5% | 75% |
| SimpleQA Verified | 11.7% | 21.6% |
| Vectara Hallucination Rate | 3.1% | 12.9% |
| LMArena Expert | 1396 | 1379 |
| Humanity's Last Exam | — | 19.4% |
| MMLU-Pro | — | 83.5% |
| Confabulations | — | 13.3% |
| GPQA (HELM) | — | 75.6% |
Multimodal GPT-5.4 nano leads
GPT-5.4 nano: 36.7 (#78), GPT-5 Mini: 35.6 (#85)
| Benchmark | GPT-5.4 nano | GPT-5 Mini |
|---|---|---|
| LMArena Vision | 1196 | 1202 |
| VPCT | — | 40.2% |
Multilingual Too close to call
GPT-5.4 nano: 48.6 (#140), GPT-5 Mini: 48.9 (#137)
| Benchmark | GPT-5.4 nano | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | 1359 | 1363 |
| LMArena Chinese | 1392 | 1385 |
| LMArena French | 1396 | 1386 |
| LMArena German | 1367 | 1366 |
| LMArena Japanese | 1343 | 1341 |
| LMArena Korean | 1320 | 1308 |
| LMArena Russian | 1363 | 1362 |
| LMArena Spanish | 1371 | 1355 |
Instruction Following GPT-5 Mini leads
GPT-5.4 nano: 71.9 (#144), GPT-5 Mini: 76.2 (#46)
| Benchmark | GPT-5.4 nano | GPT-5 Mini |
|---|---|---|
| LMArena Instruction Following | 1362 | 1357 |
| IFEval | — | 92.7% |
Long Context Too close to call
GPT-5.4 nano: 41.6 (#137), GPT-5 Mini: 41.9 (#132)
| Benchmark | GPT-5.4 nano | GPT-5 Mini |
|---|---|---|
| LMArena Longer Query | 1366 | 1355 |
| Fiction.LiveBench | — | 69.4% |
Writing & Preference Too close to call
GPT-5.4 nano: 55.7 (#142), GPT-5 Mini: 55.2 (#148)
| Benchmark | GPT-5.4 nano | GPT-5 Mini |
|---|---|---|
| LMArena Text | 1372 | 1373 |
| LMArena Creative Writing | 1314 | 1325 |
| LMArena Multi-Turn | 1382 | 1363 |
| Short-Story Creative Writing | — | 83.1% |
| EQ-Bench Creative Writing | — | 1313 |
| WildBench | — | 85.5% |
Frequently asked questions
Is GPT-5.4 nano better than GPT-5 Mini?
GPT-5.4 nano and GPT-5 Mini score almost the same on the Noometry Index (41.9 vs 41.8), so choose on price, context window or the category you care about most.
Which is cheaper, GPT-5.4 nano or GPT-5 Mini?
GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; GPT-5 Mini lists at $0.25 and $2.
Is GPT-5.4 nano or GPT-5 Mini better for coding?
GPT-5.4 nano scores higher on coding benchmarks: 43.6 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
Both accept 400K tokens.
How many benchmarks do GPT-5.4 nano and GPT-5 Mini share?
40 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and GPT-5 Mini has 60.