Model comparison
o1-mini vs Phi-2
o1-mini has enough public results to be ranked (#230); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 3 shared benchmarks.
MicrosoftSummary
- They share 3 benchmarks with published results for both.
- Phi-2 has downloadable open weights; the other is API-only.
Side by side
| o1-mini | Phi-2 | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 33.7 | — |
| Released | 2024-09-12 | 2023-12-12 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 39 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
o1-mini: 35.1 (#218), Phi-2: —
| Benchmark | o1-mini | Phi-2 |
|---|---|---|
| HumanEval+ | 89% | 45.1% |
| MBPP+ | 78.8% | 54.2% |
| Aider Polyglot | 32.9% | — |
| WeirdML | 36.3% | — |
| LiveBench Coding | 48% | — |
| LMArena Coding | 1362 | — |
Agentic & Tool Use Not comparable
o1-mini: 24.3 (#112), Phi-2: —
| Benchmark | o1-mini | Phi-2 |
|---|---|---|
| Cybench | 10% | — |
Reasoning Not comparable
o1-mini: 8.9 (#340), Phi-2: —
| Benchmark | o1-mini | Phi-2 |
|---|---|---|
| Epoch Capabilities Index | 135.82 | 107.62 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 18.1% | — |
| ARC-AGI-1 | 14% | — |
| LiveBench Reasoning | 72.3% | — |
| LMArena Hard Prompts | 1333 | — |
| LiveBench Data Analysis | 57.9% | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| HellaSwag | — | 53.6% |
| LiveBench | 57.8% | — |
| WinoGrande | — | 54.7% |
Math Not comparable
o1-mini: 33.7 (#168), Phi-2: —
| Benchmark | o1-mini | Phi-2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 46.9% | — |
| LiveBench Math | 62% | — |
| LMArena Math | 1358 | — |
| MATH Level 5 | 89.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Not comparable
o1-mini: 34.8 (#180), Phi-2: —
| Benchmark | o1-mini | Phi-2 |
|---|---|---|
| GPQA Diamond | 62.4% | — |
| Confabulations | 18.6% | — |
| LMArena Expert | 1316 | — |
| ARC (AI2) Challenge | — | 75.9% |
| MMLU | — | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Multilingual Not comparable
o1-mini: 43.8 (#177), Phi-2: —
| Benchmark | o1-mini | Phi-2 |
|---|---|---|
| LMArena Non-English | 1289 | — |
| LMArena Chinese | 1314 | — |
| LMArena French | 1292 | — |
| LMArena German | 1278 | — |
| LMArena Japanese | 1245 | — |
| LMArena Korean | 1223 | — |
| LMArena Russian | 1283 | — |
| LMArena Spanish | 1302 | — |
Instruction Following Not comparable
o1-mini: 67.0 (#200), Phi-2: —
| Benchmark | o1-mini | Phi-2 |
|---|---|---|
| LiveBench Instruction Following | 65.4% | — |
| LMArena Instruction Following | 1304 | — |
Long Context Not comparable
o1-mini: 40.1 (#156), Phi-2: —
| Benchmark | o1-mini | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1321 | — |
Writing & Preference Not comparable
o1-mini: 48.6 (#196), Phi-2: —
| Benchmark | o1-mini | Phi-2 |
|---|---|---|
| LMArena Text | 1317 | — |
| LMArena Creative Writing | 1244 | — |
| Short-Story Creative Writing | 64.9% | — |
| LMArena Multi-Turn | 1314 | — |
| LiveBench Language | 40.9% | — |
Frequently asked questions
Is o1-mini better than Phi-2?
o1-mini has enough public results to be ranked (#230); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do o1-mini and Phi-2 share?
3 benchmarks have published results for both models. o1-mini has 39 scored results on Noometry and Phi-2 has 11.