Model comparison
GPT-5.1 vs o4-mini
GPT-5.1 is the stronger model overall, scoring 49.0 to 41.6 on the Noometry Index. o4-mini costs 1.8× less per token, which makes it the better buy when GPT-5.1's lead doesn't matter for your workload.
Last verified . 46 shared benchmarks.
Summary
- They share 46 benchmarks with published results for both. GPT-5.1 scores higher in 10 categories and o4-mini in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.1 leads 39.8 to 24.6.
- The biggest single-benchmark swing is GPQA (HELM): 44.2% for GPT-5.1 and 73.5% for o4-mini.
- o4-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- GPT-5.1 accepts more context: 400K tokens versus 200K.
Side by side
| GPT-5.1 | o4-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 49.0 | 41.6 |
| Released | 2025-11-13 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $1.25 | $1.10 |
| Output $ / M tokens | $10 | $4.40 |
| Results tracked | 63 | 60 |
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), o4-mini: 40.9 (#127)
| Benchmark | GPT-5.1 | o4-mini |
|---|---|---|
| SWE-bench Verified (bash only) | 66% | 45% |
| GSO | 13.7% | 3.6% |
| WeirdML | 60.8% | 52.6% |
| LMArena Coding | 1454 | 1368 |
| ALE-Bench | 1,192 | 826.17 |
| SWE-bench Verified | 68% | — |
| Aider Polyglot | — | 72% |
| LMArena WebDev | 1395 | — |
| SciCode | 43.3% | — |
| LiveBench Coding | 72.5% | — |
| CadEval | — | 62% |
| AlgoTune | — | 1.72 |
Agentic & Tool Use Too close to call
GPT-5.1: 32.7 (#60), o4-mini: 32.6 (#61)
| Benchmark | GPT-5.1 | o4-mini |
|---|---|---|
| Terminal-Bench | 47.6% | — |
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
| DeepResearch Bench | 42.8% | — |
| LMArena Search | 1199 | — |
| METR Time Horizons | — | 63.9% |
| Vending-Bench 2 | 1,473 | — |
Reasoning GPT-5.1 leads
GPT-5.1: 39.8 (#58), o4-mini: 24.6 (#162)
| Benchmark | GPT-5.1 | o4-mini |
|---|---|---|
| ARC-AGI-2 | 17.6% | 6.1% |
| SimpleBench | 53.2% | 38.7% |
| ARC-AGI-1 | 72.8% | 58.7% |
| CritPt | 4.9% | 0.6% |
| Chess Puzzles | 32% | 26% |
| EnigmaEval | 11.2% | 9.2% |
| LMArena Hard Prompts | 1457 | 1351 |
| Mystery Game Puzzles | 19% | 5% |
| DTBench | 90.1% | 77.6% |
| LMCA | 43.9% | 26.5% |
| Epoch Capabilities Index | 149.64 | 145.64 |
| ForecastBench | 58.1 | 61.8 |
| Kagi LLM Benchmark | — | 67.6% |
| LiveBench Reasoning | 95.8% | — |
| LiveBench Data Analysis | 72.1% | — |
| LiveBench | 78.8% | — |
Math GPT-5.1 leads
GPT-5.1: 52.2 (#51), o4-mini: 40.8 (#89)
| Benchmark | GPT-5.1 | o4-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.6% | 81.7% |
| Omni-MATH | 46.4% | 72% |
| LMArena Math | 1447 | 1389 |
| FrontierMath (Feb 2025 set) | 31% | 24.8% |
| FrontierMath Tier 4 (v1) | 12.5% | 6.3% |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| LiveBench Math | 94.5% | — |
| MATH Level 5 | — | 97.8% |
Knowledge GPT-5.1 leads
GPT-5.1: 50.6 (#71), o4-mini: 43.6 (#91)
| Benchmark | GPT-5.1 | o4-mini |
|---|---|---|
| GPQA Diamond | 87.6% | 79.6% |
| Humanity's Last Exam | 23.7% | 18.1% |
| SimpleQA Verified | 48% | 19.6% |
| MMLU-Pro | 57.9% | 82% |
| Vectara Hallucination Rate | 10.9% | 18.6% |
| GPQA (HELM) | 44.2% | 73.5% |
| LMArena Expert | 1470 | 1343 |
| Confabulations | — | 15.8% |
Multimodal GPT-5.1 leads
GPT-5.1: 44.8 (#19), o4-mini: 40.2 (#49)
| Benchmark | GPT-5.1 | o4-mini |
|---|---|---|
| LMArena Vision | 1250 | 1194 |
| VPCT | 58.7% | 57.5% |
| GeoBench | — | 64% |
| LMArena Document | 1403 | — |
Multilingual GPT-5.1 leads
GPT-5.1: 53.8 (#56), o4-mini: 47.0 (#154)
| Benchmark | GPT-5.1 | o4-mini |
|---|---|---|
| LMArena Non-English | 1431 | 1337 |
| LMArena Chinese | 1495 | 1354 |
| LMArena French | 1450 | 1364 |
| LMArena German | 1438 | 1336 |
| LMArena Japanese | 1453 | 1308 |
| LMArena Korean | 1401 | 1312 |
| LMArena Russian | 1435 | 1334 |
| LMArena Spanish | 1433 | 1347 |
Instruction Following GPT-5.1 leads
GPT-5.1: 83.9 (#1), o4-mini: 75.2 (#68)
| Benchmark | GPT-5.1 | o4-mini |
|---|---|---|
| IFEval | 93.5% | 92.8% |
| LMArena Instruction Following | 1443 | 1321 |
| LiveBench Instruction Following | 93.3% | — |
Long Context GPT-5.1 leads
GPT-5.1: 47.6 (#14), o4-mini: 45.5 (#33)
| Benchmark | GPT-5.1 | o4-mini |
|---|---|---|
| LMArena Longer Query | 1447 | 1315 |
| Fiction.LiveBench | — | 77.8% |
| CL-bench | 23.7% | — |
| CL-bench Life | 17.3% | — |
Writing & Preference GPT-5.1 leads
GPT-5.1: 64.5 (#55), o4-mini: 54.0 (#152)
| Benchmark | GPT-5.1 | o4-mini |
|---|---|---|
| LMArena Text | 1443 | 1353 |
| LMArena Creative Writing | 1427 | 1294 |
| WildBench | 86.3% | 85.4% |
| LMArena Multi-Turn | 1450 | 1350 |
| Short-Story Creative Writing | — | 75% |
| LiveBench Language | 80.2% | — |
Frequently asked questions
Is GPT-5.1 better than o4-mini?
GPT-5.1 is the stronger model overall, scoring 49.0 to 41.6 on the Noometry Index. o4-mini costs 1.8× 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 o4-mini?
o4-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; GPT-5.1 lists at $1.25 and $10.
Is GPT-5.1 or o4-mini better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.4 versus 40.9 in the Noometry coding category.
Which has the bigger context window?
GPT-5.1 does, with 400K tokens against 200K.
How many benchmarks do GPT-5.1 and o4-mini share?
46 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and o4-mini has 60.