Model comparison
GPT-4 vs GPT-5.4 mini
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 29.1 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. GPT-4 scores higher in 0 categories and GPT-5.4 mini in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 mini leads 45.5 to 10.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for GPT-4 and 88.9% for GPT-5.4 mini.
- GPT-5.4 mini is cheaper at $0.75 / $4.50 per million input/output tokens, against $30 / $60 for GPT-4.
- GPT-5.4 mini accepts more context: 400K tokens versus 8K.
Side by side
| GPT-4 | GPT-5.4 mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 29.1 | 45.0 |
| Released | 2023-03-14 | 2026-03-17 |
| Weights | Proprietary | Proprietary |
| Context window | 8K | 400K |
| Max output | 8K | 128K |
| Input $ / M tokens | $30 | $0.75 |
| Output $ / M tokens | $60 | $4.50 |
| Results tracked | 38 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
GPT-4: 31.6 (#283), GPT-5.4 mini: 45.2 (#72)
| Benchmark | GPT-4 | GPT-5.4 mini |
|---|---|---|
| WeirdML | 12.4% | 60.3% |
| LMArena Coding | 1254 | 1438 |
| FrontierCode | — | 27% |
| LMArena WebDev | — | 1397 |
| SciCode | — | 49.9% |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| ALE-Bench | — | 1,189 |
| HumanEval+ | 79.3% | — |
Agentic & Tool Use Not comparable
GPT-4: —, GPT-5.4 mini: 29.9 (#81)
| Benchmark | GPT-4 | GPT-5.4 mini |
|---|---|---|
| DeepResearch Bench | — | 36.3% |
| METR Time Horizons | 36.1% | — |
Reasoning GPT-5.4 mini leads
GPT-4: 17.8 (#289), GPT-5.4 mini: 30.4 (#85)
| Benchmark | GPT-4 | GPT-5.4 mini |
|---|---|---|
| Chess Puzzles | 4% | 24% |
| LMArena Hard Prompts | 1241 | 1424 |
| Mystery Game Puzzles | 12% | 11% |
| DTBench | 62.7% | 80% |
| LMCA | 17.1% | 40.8% |
| Epoch Capabilities Index | 125.89 | 148.84 |
| ForecastBench | 57.8 | 57 |
| ARC-AGI-2 | — | 18.9% |
| Kagi LLM Benchmark | — | 37.9% |
| NYT Connections (extended) | — | 61.8% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | — | 10% |
| Thematic Generalization | — | 61.7% |
| BIG-Bench Hard | 75.1% | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |
Math GPT-5.4 mini leads
GPT-4: 10.8 (#309), GPT-5.4 mini: 45.5 (#75)
| Benchmark | GPT-4 | GPT-5.4 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 88.9% |
| LMArena Math | 1269 | 1419 |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 9.8% |
| ProofBench | — | 21% |
| MATH Level 5 | 23% | — |
| FrontierMath (Feb 2025 set) | — | 28.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
| GSM8K | 92% | — |
Knowledge GPT-5.4 mini leads
GPT-4: 18.4 (#282), GPT-5.4 mini: 51.5 (#67)
| Benchmark | GPT-4 | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | 35.7% | 86.9% |
| LMArena Expert | 1211 | 1435 |
| SimpleQA Verified | — | 29.4% |
| Vectara Hallucination Rate | — | 5.5% |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |
Multimodal Not comparable
GPT-4: —, GPT-5.4 mini: 39.7 (#56)
| Benchmark | GPT-4 | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual GPT-5.4 mini leads
GPT-4: 40.6 (#215), GPT-5.4 mini: 51.9 (#96)
| Benchmark | GPT-4 | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1246 | 1405 |
| LMArena Chinese | 1242 | 1446 |
| LMArena French | 1283 | 1440 |
| LMArena German | 1251 | 1409 |
| LMArena Japanese | 1209 | 1374 |
| LMArena Korean | 1184 | 1368 |
| LMArena Russian | 1251 | 1417 |
| LMArena Spanish | 1261 | 1405 |
Instruction Following GPT-5.4 mini leads
GPT-4: 65.3 (#222), GPT-5.4 mini: 74.1 (#102)
| Benchmark | GPT-4 | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1241 | 1405 |
Long Context GPT-5.4 mini leads
GPT-4: 37.7 (#212), GPT-5.4 mini: 43.0 (#112)
| Benchmark | GPT-4 | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1244 | 1407 |
Writing & Preference GPT-5.4 mini leads
GPT-4: 34.9 (#268), GPT-5.4 mini: 64.0 (#58)
| Benchmark | GPT-4 | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1263 | 1412 |
| LMArena Creative Writing | 1244 | 1370 |
| EQ-Bench Creative Writing | 752 | 1665 |
| LMArena Multi-Turn | 1257 | 1429 |
Frequently asked questions
Is GPT-4 better than GPT-5.4 mini?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 29.1 on the Noometry Index.
Which is cheaper, GPT-4 or GPT-5.4 mini?
GPT-5.4 mini is cheaper. It lists at $0.75 per million input tokens and $4.50 per million output tokens; GPT-4 lists at $30 and $60.
Is GPT-4 or GPT-5.4 mini better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 31.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 mini does, with 400K tokens against 8K.
How many benchmarks do GPT-4 and GPT-5.4 mini share?
27 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and GPT-5.4 mini has 46.