Model comparison
GPT-5.4 Pro vs GPT-5 Mini
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 41.8 on the Noometry Index. GPT-5 Mini costs 98× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
Summary
- They share 15 benchmarks with published results for both. GPT-5.4 Pro scores higher in 4 categories and GPT-5 Mini in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 Pro leads 70.7 to 23.9.
- The biggest single-benchmark swing is ARC-AGI-2: 83.3% for GPT-5.4 Pro and 4.4% for GPT-5 Mini.
- GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $30 / $180 for GPT-5.4 Pro.
- GPT-5.4 Pro accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-5.4 Pro | GPT-5 Mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 58.9 | 41.8 |
| Released | 2026-03-05 | 2025-08-07 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 400K |
| Max output | 128K | 128K |
| Input $ / M tokens | $30 | $0.25 |
| Output $ / M tokens | $180 | $2 |
| Results tracked | 16 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 Pro leads
GPT-5.4 Pro: 43.2 (#90), GPT-5 Mini: 40.1 (#146)
| Benchmark | GPT-5.4 Pro | GPT-5 Mini |
|---|---|---|
| WeirdML | 57.4% | 52.7% |
| SWE-bench Verified | — | 64.7% |
| SWE-bench Verified (bash only) | — | 59.8% |
| SWE-bench Multilingual | — | 39.7% |
| SciCode | — | 39.2% |
| LMArena Coding | — | 1406 |
| ALE-Bench | — | 799.77 |
| AlgoTune | — | 1.38 |
Agentic & Tool Use Not comparable
GPT-5.4 Pro: —, GPT-5 Mini: 31.1 (#70)
| Benchmark | GPT-5.4 Pro | GPT-5 Mini |
|---|---|---|
| Terminal-Bench | — | 34.8% |
| Berkeley Function Calling Leaderboard | — | 55.5% |
| Vending-Bench 2 | — | -31.18 |
Reasoning GPT-5.4 Pro leads
GPT-5.4 Pro: 70.7 (#13), GPT-5 Mini: 23.9 (#168)
| Benchmark | GPT-5.4 Pro | GPT-5 Mini |
|---|---|---|
| ARC-AGI-2 | 83.3% | 4.4% |
| ARC-AGI-1 | 94.5% | 54.3% |
| CritPt | 30% | 0% |
| Chess Puzzles | 58.6% | 30% |
| EnigmaEval | 23.8% | 8.2% |
| Epoch Capabilities Index | 158.93 | 145.52 |
| SimpleBench | 74.1% | — |
| Kagi LLM Benchmark | — | 70.3% |
| LMArena Hard Prompts | — | 1380 |
| Mystery Game Puzzles | — | 10% |
| DTBench | — | 80.5% |
| LMCA | — | 34.2% |
| ForecastBench | — | 61 |
Math GPT-5.4 Pro leads
GPT-5.4 Pro: 72.4 (#22), GPT-5 Mini: 46.7 (#69)
| Benchmark | GPT-5.4 Pro | GPT-5 Mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | 46.7% |
| FrontierMath Tier 4 | 58.5% | 12.2% |
| FrontierMath (Feb 2025 set) | 50% | 27.2% |
| FrontierMath Tier 4 (v1) | 37.5% | 6.3% |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 9% |
| Omni-MATH | — | 72.2% |
| LMArena Math | — | 1378 |
| MATH Level 5 | — | 97.8% |
Knowledge GPT-5.4 Pro leads
GPT-5.4 Pro: 68.3 (#7), GPT-5 Mini: 45.6 (#86)
| Benchmark | GPT-5.4 Pro | GPT-5 Mini |
|---|---|---|
| GPQA Diamond | 94.6% | 75% |
| Humanity's Last Exam | 44.3% | 19.4% |
| SimpleQA Verified | 46.3% | 21.6% |
| Vectara Hallucination Rate | 8.3% | 12.9% |
| MMLU-Pro | — | 83.5% |
| Confabulations | — | 13.3% |
| GPQA (HELM) | — | 75.6% |
| LMArena Expert | — | 1379 |
Multimodal Not comparable
GPT-5.4 Pro: —, GPT-5 Mini: 35.6 (#85)
| Benchmark | GPT-5.4 Pro | GPT-5 Mini |
|---|---|---|
| LMArena Vision | — | 1202 |
| VPCT | — | 40.2% |
Multilingual Not comparable
GPT-5.4 Pro: —, GPT-5 Mini: 48.9 (#137)
| Benchmark | GPT-5.4 Pro | GPT-5 Mini |
|---|---|---|
| LMArena Non-English | — | 1363 |
| LMArena Chinese | — | 1385 |
| LMArena French | — | 1386 |
| LMArena German | — | 1366 |
| LMArena Japanese | — | 1341 |
| LMArena Korean | — | 1308 |
| LMArena Russian | — | 1362 |
| LMArena Spanish | — | 1355 |
Instruction Following Not comparable
GPT-5.4 Pro: —, GPT-5 Mini: 76.2 (#46)
| Benchmark | GPT-5.4 Pro | GPT-5 Mini |
|---|---|---|
| IFEval | — | 92.7% |
| LMArena Instruction Following | — | 1357 |
Long Context Not comparable
GPT-5.4 Pro: —, GPT-5 Mini: 41.9 (#132)
| Benchmark | GPT-5.4 Pro | GPT-5 Mini |
|---|---|---|
| Fiction.LiveBench | — | 69.4% |
| LMArena Longer Query | — | 1355 |
Writing & Preference Not comparable
GPT-5.4 Pro: —, GPT-5 Mini: 55.2 (#148)
| Benchmark | GPT-5.4 Pro | GPT-5 Mini |
|---|---|---|
| LMArena Text | — | 1373 |
| LMArena Creative Writing | — | 1325 |
| Short-Story Creative Writing | — | 83.1% |
| EQ-Bench Creative Writing | — | 1313 |
| WildBench | — | 85.5% |
| LMArena Multi-Turn | — | 1363 |
Frequently asked questions
Is GPT-5.4 Pro better than GPT-5 Mini?
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 41.8 on the Noometry Index. GPT-5 Mini costs 98× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-5.4 Pro or GPT-5 Mini?
GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; GPT-5.4 Pro lists at $30 and $180.
Is GPT-5.4 Pro or GPT-5 Mini better for coding?
GPT-5.4 Pro scores higher on coding benchmarks: 43.2 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 Pro does, with 1.05M tokens against 400K.
How many benchmarks do GPT-5.4 Pro and GPT-5 Mini share?
15 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and GPT-5 Mini has 60.