Model comparison
GPT-4.1 mini vs GPT-5.4 mini
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 33.6 on the Noometry Index. GPT-4.1 mini costs 2.4× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. GPT-4.1 mini scores higher in 1 category and GPT-5.4 mini in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 mini leads 45.5 to 24.1.
- The biggest single-benchmark swing is ARC-AGI-1: 3.5% for GPT-4.1 mini and 63.7% for GPT-5.4 mini.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-4.1 mini | GPT-5.4 mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 33.6 | 45.0 |
| Released | 2025-04-14 | 2026-03-17 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 33K | 128K |
| Input $ / M tokens | $0.40 | $0.75 |
| Output $ / M tokens | $1.60 | $4.50 |
| Results tracked | 47 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
GPT-4.1 mini: 30.6 (#293), GPT-5.4 mini: 45.2 (#72)
| Benchmark | GPT-4.1 mini | GPT-5.4 mini |
|---|---|---|
| SciCode | 40.4% | 49.9% |
| WeirdML | 37.6% | 60.3% |
| LMArena Coding | 1367 | 1438 |
| FrontierCode | — | 27% |
| SWE-bench Verified (bash only) | 23.9% | — |
| Aider Polyglot | 32.4% | — |
| LMArena WebDev | — | 1397 |
| BigCodeBench Instruct | 48.9% | — |
| CadEval | 16% | — |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use GPT-4.1 mini leads
GPT-4.1 mini: 33.3 (#55), GPT-5.4 mini: 29.9 (#81)
| Benchmark | GPT-4.1 mini | GPT-5.4 mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | — |
| DeepResearch Bench | — | 36.3% |
Reasoning GPT-5.4 mini leads
GPT-4.1 mini: 10.8 (#340), GPT-5.4 mini: 30.4 (#85)
| Benchmark | GPT-4.1 mini | GPT-5.4 mini |
|---|---|---|
| ARC-AGI-2 | 0% | 18.9% |
| Kagi LLM Benchmark | 48.6% | 37.9% |
| ARC-AGI-1 | 3.5% | 63.7% |
| CritPt | 0% | 10% |
| Chess Puzzles | 7% | 24% |
| LMArena Hard Prompts | 1349 | 1424 |
| Mystery Game Puzzles | 7% | 11% |
| DTBench | 68.8% | 80% |
| LMCA | 21.1% | 40.8% |
| Epoch Capabilities Index | 135.01 | 148.84 |
| NYT Connections (extended) | — | 61.8% |
| Thematic Generalization | — | 61.7% |
| ForecastBench | — | 57 |
Math GPT-5.4 mini leads
GPT-4.1 mini: 24.1 (#270), GPT-5.4 mini: 45.5 (#75)
| Benchmark | GPT-4.1 mini | GPT-5.4 mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 6.7% | 51.2% |
| OTIS Mock AIME 2024-2025 | 44.7% | 88.9% |
| LMArena Math | 1343 | 1419 |
| FrontierMath (Feb 2025 set) | 4.5% | 28.3% |
| FrontierMath Tier 4 | — | 9.8% |
| ProofBench | — | 21% |
| Omni-MATH | 49.1% | — |
| MATH Level 5 | 87.3% | — |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GPT-5.4 mini leads
GPT-4.1 mini: 34.7 (#194), GPT-5.4 mini: 51.5 (#67)
| Benchmark | GPT-4.1 mini | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | 65.8% | 86.9% |
| SimpleQA Verified | 12.7% | 29.4% |
| LMArena Expert | 1338 | 1435 |
| MMLU-Pro | 78.3% | — |
| Vectara Hallucination Rate | — | 5.5% |
| GPQA (HELM) | 61.4% | — |
Multimodal GPT-5.4 mini leads
GPT-4.1 mini: 35.8 (#82), GPT-5.4 mini: 39.7 (#56)
| Benchmark | GPT-4.1 mini | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | 1181 | 1245 |
Multilingual GPT-5.4 mini leads
GPT-4.1 mini: 45.7 (#166), GPT-5.4 mini: 51.9 (#96)
| Benchmark | GPT-4.1 mini | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1318 | 1405 |
| LMArena Chinese | 1329 | 1446 |
| LMArena French | 1358 | 1440 |
| LMArena German | 1351 | 1409 |
| LMArena Japanese | 1290 | 1374 |
| LMArena Korean | 1298 | 1368 |
| LMArena Russian | 1324 | 1417 |
| LMArena Spanish | 1319 | 1405 |
Instruction Following Too close to call
GPT-4.1 mini: 73.7 (#118), GPT-5.4 mini: 74.1 (#102)
| Benchmark | GPT-4.1 mini | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1333 | 1405 |
| IFEval | 90.4% | — |
Long Context GPT-5.4 mini leads
GPT-4.1 mini: 31.8 (#275), GPT-5.4 mini: 43.0 (#112)
| Benchmark | GPT-4.1 mini | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1344 | 1407 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference GPT-5.4 mini leads
GPT-4.1 mini: 48.6 (#199), GPT-5.4 mini: 64.0 (#58)
| Benchmark | GPT-4.1 mini | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1340 | 1412 |
| LMArena Creative Writing | 1300 | 1370 |
| EQ-Bench Creative Writing | 1147 | 1665 |
| LMArena Multi-Turn | 1354 | 1429 |
| WildBench | 83.8% | — |
Frequently asked questions
Is GPT-4.1 mini better than GPT-5.4 mini?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 33.6 on the Noometry Index. GPT-4.1 mini costs 2.4× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 mini or GPT-5.4 mini?
GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.
Is GPT-4.1 mini or GPT-5.4 mini better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 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-5.4 mini share?
35 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and GPT-5.4 mini has 46.