Model comparison
GPT-5.1 vs GPT-5.4 mini
GPT-5.1 is the stronger model overall, scoring 49.0 to 45.0 on the Noometry Index. GPT-5.4 mini costs 2.0× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Last verified . 38 shared benchmarks.
Summary
- They share 38 benchmarks with published results for both. GPT-5.1 scores higher in 9 categories and GPT-5.4 mini in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where GPT-5.1 leads 83.9 to 74.1.
- The biggest single-benchmark swing is SimpleQA Verified: 48% for GPT-5.1 and 29.4% for GPT-5.4 mini.
- GPT-5.4 mini is cheaper at $0.75 / $4.50 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
Side by side
| GPT-5.1 | GPT-5.4 mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 49.0 | 45.0 |
| Released | 2025-11-13 | 2026-03-17 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 400K |
| Max output | 128K | 128K |
| Input $ / M tokens | $1.25 | $0.75 |
| Output $ / M tokens | $10 | $4.50 |
| Results tracked | 63 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
GPT-5.1: 46.4 (#66), GPT-5.4 mini: 45.2 (#72)
| Benchmark | GPT-5.1 | GPT-5.4 mini |
|---|---|---|
| LMArena WebDev | 1395 | 1397 |
| SciCode | 43.3% | 49.9% |
| WeirdML | 60.8% | 60.3% |
| LMArena Coding | 1454 | 1438 |
| ALE-Bench | 1,192 | 1,189 |
| SWE-bench Verified | 68% | — |
| FrontierCode | — | 27% |
| SWE-bench Verified (bash only) | 66% | — |
| GSO | 13.7% | — |
| LiveBench Coding | 72.5% | — |
Agentic & Tool Use GPT-5.1 leads
GPT-5.1: 32.7 (#60), GPT-5.4 mini: 29.9 (#81)
| Benchmark | GPT-5.1 | GPT-5.4 mini |
|---|---|---|
| DeepResearch Bench | 42.8% | 36.3% |
| Terminal-Bench | 47.6% | — |
| LMArena Search | 1199 | — |
| Vending-Bench 2 | 1,473 | — |
Reasoning GPT-5.1 leads
GPT-5.1: 39.8 (#58), GPT-5.4 mini: 30.4 (#85)
| Benchmark | GPT-5.1 | GPT-5.4 mini |
|---|---|---|
| ARC-AGI-2 | 17.6% | 18.9% |
| ARC-AGI-1 | 72.8% | 63.7% |
| CritPt | 4.9% | 10% |
| Chess Puzzles | 32% | 24% |
| LMArena Hard Prompts | 1457 | 1424 |
| Mystery Game Puzzles | 19% | 11% |
| DTBench | 90.1% | 80% |
| LMCA | 43.9% | 40.8% |
| Epoch Capabilities Index | 149.64 | 148.84 |
| ForecastBench | 58.1 | 57 |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | — | 37.9% |
| NYT Connections (extended) | — | 61.8% |
| EnigmaEval | 11.2% | — |
| Thematic Generalization | — | 61.7% |
| LiveBench Reasoning | 95.8% | — |
| LiveBench Data Analysis | 72.1% | — |
| LiveBench | 78.8% | — |
Math GPT-5.1 leads
GPT-5.1: 52.2 (#51), GPT-5.4 mini: 45.5 (#75)
| Benchmark | GPT-5.1 | GPT-5.4 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.6% | 88.9% |
| LMArena Math | 1447 | 1419 |
| FrontierMath (Feb 2025 set) | 31% | 28.3% |
| FrontierMath Tier 4 (v1) | 12.5% | 2.1% |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 9.8% |
| ProofBench | — | 21% |
| Omni-MATH | 46.4% | — |
| LiveBench Math | 94.5% | — |
Knowledge Too close to call
GPT-5.1: 50.6 (#71), GPT-5.4 mini: 51.5 (#67)
| Benchmark | GPT-5.1 | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | 87.6% | 86.9% |
| SimpleQA Verified | 48% | 29.4% |
| Vectara Hallucination Rate | 10.9% | 5.5% |
| LMArena Expert | 1470 | 1435 |
| Humanity's Last Exam | 23.7% | — |
| MMLU-Pro | 57.9% | — |
| GPQA (HELM) | 44.2% | — |
Multimodal GPT-5.1 leads
GPT-5.1: 44.8 (#19), GPT-5.4 mini: 39.7 (#56)
| Benchmark | GPT-5.1 | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | 1250 | 1245 |
| VPCT | 58.7% | — |
| LMArena Document | 1403 | — |
Multilingual GPT-5.1 leads
GPT-5.1: 53.8 (#56), GPT-5.4 mini: 51.9 (#96)
| Benchmark | GPT-5.1 | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1431 | 1405 |
| LMArena Chinese | 1495 | 1446 |
| LMArena French | 1450 | 1440 |
| LMArena German | 1438 | 1409 |
| LMArena Japanese | 1453 | 1374 |
| LMArena Korean | 1401 | 1368 |
| LMArena Russian | 1435 | 1417 |
| LMArena Spanish | 1433 | 1405 |
Instruction Following GPT-5.1 leads
GPT-5.1: 83.9 (#1), GPT-5.4 mini: 74.1 (#102)
| Benchmark | GPT-5.1 | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1443 | 1405 |
| LiveBench Instruction Following | 93.3% | — |
| IFEval | 93.5% | — |
Long Context GPT-5.1 leads
GPT-5.1: 47.6 (#14), GPT-5.4 mini: 43.0 (#112)
| Benchmark | GPT-5.1 | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1447 | 1407 |
| CL-bench | 23.7% | — |
| CL-bench Life | 17.3% | — |
Writing & Preference Too close to call
GPT-5.1: 64.5 (#55), GPT-5.4 mini: 64.0 (#58)
| Benchmark | GPT-5.1 | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1443 | 1412 |
| LMArena Creative Writing | 1427 | 1370 |
| LMArena Multi-Turn | 1450 | 1429 |
| EQ-Bench Creative Writing | — | 1665 |
| WildBench | 86.3% | — |
| LiveBench Language | 80.2% | — |
Frequently asked questions
Is GPT-5.1 better than GPT-5.4 mini?
GPT-5.1 is the stronger model overall, scoring 49.0 to 45.0 on the Noometry Index. GPT-5.4 mini costs 2.0× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Which is cheaper, GPT-5.1 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-5.1 lists at $1.25 and $10.
Is GPT-5.1 or GPT-5.4 mini better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.4 versus 45.2 in the Noometry coding category.
Which has the bigger context window?
Both accept 400K tokens.
How many benchmarks do GPT-5.1 and GPT-5.4 mini share?
38 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and GPT-5.4 mini has 46.