Model comparison
GPT-4o mini vs o1-mini
o1-mini is the stronger model overall, scoring 34.0 to 25.5 on the Noometry Index.
Last verified . 36 shared benchmarks.
Summary
- They share 36 benchmarks with published results for both. GPT-4o mini scores higher in 1 category and o1-mini in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where o1-mini leads 35.4 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.9% for GPT-4o mini and 46.9% for o1-mini.
Side by side
| GPT-4o mini | o1-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 25.5 | 34.0 |
| Released | 2024-07-18 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 60 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1-mini leads
GPT-4o mini: 22.0 (#335), o1-mini: 35.5 (#224)
| Benchmark | GPT-4o mini | o1-mini |
|---|---|---|
| Aider Polyglot | 3.6% | 32.9% |
| WeirdML | 11.8% | 36.3% |
| LiveBench Coding | 43.1% | 48% |
| LMArena Coding | 1290 | 1362 |
| HumanEval+ | 83.5% | 89% |
| MBPP+ | 72.2% | 78.8% |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 57.4% | — |
Agentic & Tool Use GPT-4o mini leads
GPT-4o mini: 27.5 (#101), o1-mini: 24.6 (#118)
Reasoning Too close to call
GPT-4o mini: 8.7 (#347), o1-mini: 8.8 (#346)
| Benchmark | GPT-4o mini | o1-mini |
|---|---|---|
| ARC-AGI-2 | 0% | 0.8% |
| SimpleBench | 10.7% | 18.1% |
| LiveBench Reasoning | 32.8% | 72.3% |
| LMArena Hard Prompts | 1267 | 1333 |
| LiveBench Data Analysis | 50% | 57.9% |
| Epoch Capabilities Index | 126.56 | 135.82 |
| LiveBench | 41.3% | 57.8% |
| Kagi LLM Benchmark | 28.8% | — |
| ARC-AGI-1 | — | 14% |
| Chess Puzzles | 0% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 54.4% | — |
| LMCA | 10.4% | — |
| PIQA | 88.7% | — |
Math o1-mini leads
GPT-4o mini: 10.4 (#314), o1-mini: 35.4 (#186)
| Benchmark | GPT-4o mini | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.9% | 46.9% |
| LiveBench Math | 36.3% | 62% |
| LMArena Math | 1267 | 1358 |
| MATH Level 5 | 52.6% | 89.2% |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| Omni-MATH | 28% | — |
| FrontierMath (Feb 2025 set) | — | 1.7% |
| GSM8K | 91.3% | — |
Knowledge o1-mini leads
GPT-4o mini: 17.7 (#284), o1-mini: 34.9 (#192)
| Benchmark | GPT-4o mini | o1-mini |
|---|---|---|
| GPQA Diamond | 37.7% | 62.4% |
| Confabulations | 37.2% | 18.6% |
| LMArena Expert | 1235 | 1316 |
| SimpleQA Verified | 8.3% | — |
| MMLU-Pro | 60.3% | — |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |
Multimodal Not comparable
GPT-4o mini: 25.9 (#122), o1-mini: —
| Benchmark | GPT-4o mini | o1-mini |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
Multilingual o1-mini leads
GPT-4o mini: 42.0 (#199), o1-mini: 43.6 (#182)
| Benchmark | GPT-4o mini | o1-mini |
|---|---|---|
| LMArena Non-English | 1266 | 1289 |
| LMArena Chinese | 1265 | 1314 |
| LMArena French | 1297 | 1293 |
| LMArena German | 1272 | 1278 |
| LMArena Japanese | 1216 | 1245 |
| LMArena Korean | 1195 | 1223 |
| LMArena Russian | 1275 | 1283 |
| LMArena Spanish | 1276 | 1303 |
Instruction Following o1-mini leads
GPT-4o mini: 61.9 (#239), o1-mini: 66.7 (#206)
| Benchmark | GPT-4o mini | o1-mini |
|---|---|---|
| LiveBench Instruction Following | 56.8% | 65.4% |
| LMArena Instruction Following | 1258 | 1304 |
| IFEval | 78.2% | — |
Long Context o1-mini leads
GPT-4o mini: 39.1 (#186), o1-mini: 40.1 (#161)
| Benchmark | GPT-4o mini | o1-mini |
|---|---|---|
| LMArena Longer Query | 1289 | 1320 |
Writing & Preference o1-mini leads
GPT-4o mini: 39.5 (#248), o1-mini: 48.4 (#202)
| Benchmark | GPT-4o mini | o1-mini |
|---|---|---|
| LMArena Text | 1286 | 1317 |
| LMArena Creative Writing | 1268 | 1244 |
| Short-Story Creative Writing | 67.2% | 64.9% |
| LMArena Multi-Turn | 1285 | 1314 |
| LiveBench Language | 28.6% | 40.9% |
| EQ-Bench Creative Writing | 873 | — |
| WildBench | 79.1% | — |
Frequently asked questions
Is GPT-4o mini better than o1-mini?
o1-mini is the stronger model overall, scoring 34.0 to 25.5 on the Noometry Index.
Is GPT-4o mini or o1-mini better for coding?
o1-mini scores higher on coding benchmarks: 35.5 versus 22.0 in the Noometry coding category.
How many benchmarks do GPT-4o mini and o1-mini share?
36 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and o1-mini has 39.