Model comparison
o1 vs Phi 3 Mini 4k Instruct
o1 is the stronger model overall, scoring 40.9 to 27.9 on the Noometry Index.
Last verified . 27 shared benchmarks.
MicrosoftSummary
- They share 27 benchmarks with published results for both. o1 scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where o1 leads 55.6 to 27.6.
- The biggest single-benchmark swing is LiveBench Reasoning: 91.6% for o1 and 26.8% for Phi 3 Mini 4k Instruct.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| o1 | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 40.9 | 27.9 |
| Released | 2024-09-12 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 100K | — |
| Input $ / M tokens | $15 | — |
| Output $ / M tokens | $60 | — |
| Results tracked | 52 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
o1: 46.1 (#70), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | o1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Coding | 69.7% | 15.5% |
| LMArena Coding | 1367 | 1093 |
| HumanEval+ | 89% | 59.1% |
| MBPP+ | 80.2% | 54.2% |
| Aider Polyglot | 61.7% | — |
| WeirdML | 47.6% | — |
| CadEval | 56% | — |
Agentic & Tool Use Not comparable
o1: 24.6 (#117), Phi 3 Mini 4k Instruct: —
| Benchmark | o1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Cybench | 10% | — |
| METR Time Horizons | 51.1% | — |
Reasoning o1 leads
o1: 27.9 (#111), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | o1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 15% | 0% |
| LiveBench Reasoning | 91.6% | 26.8% |
| LMArena Hard Prompts | 1371 | 1072 |
| LiveBench Data Analysis | 65.5% | 34.7% |
| LiveBench | 75.7% | 22.4% |
| SimpleBench | 41.7% | — |
| ARC-AGI-1 | 30.7% | — |
| EnigmaEval | 5.7% | — |
| DTBench | 74.7% | — |
| LMCA | 22.3% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 141.91 | — |
| HellaSwag | — | 76.7% |
| WinoGrande | — | 70.8% |
Math o1 leads
o1: 36.1 (#175), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | o1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Math | 80.3% | 15.7% |
| LMArena Math | 1388 | 1111 |
| FrontierMath (Tiers 1-3) | 14.7% | — |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| MATH Level 5 | 94.7% | — |
| FrontierMath (Feb 2025 set) | 9.3% | — |
Knowledge o1 leads
o1: 41.5 (#110), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | o1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1361 | 1045 |
| GPQA Diamond | 76.8% | — |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | 41.1% | — |
| Confabulations | 11.7% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multimodal Not comparable
o1: 34.2 (#93), Phi 3 Mini 4k Instruct: —
| Benchmark | o1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1168 | — |
| GeoBench | 80% | — |
| VPCT | 37% | — |
| SpatialViz-Bench | 41.4% | — |
Multilingual o1 leads
o1: 48.6 (#142), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | o1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1358 | 1021 |
| LMArena Chinese | 1394 | 1021 |
| LMArena French | 1344 | 1076 |
| LMArena German | 1337 | 1044 |
| LMArena Japanese | 1346 | 935 |
| LMArena Korean | 1396 | 905 |
| LMArena Russian | 1356 | 1022 |
| LMArena Spanish | 1345 | 1085 |
Instruction Following o1 leads
o1: 74.8 (#86), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | o1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Instruction Following | 81.5% | 39.1% |
| LMArena Instruction Following | 1367 | 1053 |
Long Context o1 leads
o1: 50.3 (#9), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | o1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1378 | 1044 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference o1 leads
o1: 55.6 (#144), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | o1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1366 | 1073 |
| LMArena Creative Writing | 1348 | 1037 |
| LMArena Multi-Turn | 1369 | 1018 |
| LiveBench Language | 65.4% | 9.2% |
| Short-Story Creative Writing | 70.2% | — |
Frequently asked questions
Is o1 better than Phi 3 Mini 4k Instruct?
o1 is the stronger model overall, scoring 40.9 to 27.9 on the Noometry Index.
Is o1 or Phi 3 Mini 4k Instruct better for coding?
o1 scores higher on coding benchmarks: 46.1 versus 26.6 in the Noometry coding category.
How many benchmarks do o1 and Phi 3 Mini 4k Instruct share?
27 benchmarks have published results for both models. o1 has 52 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.