Model comparison
o3-mini vs Phi 3 Mini 4k Instruct
o3-mini is the stronger model overall, scoring 36.7 to 27.9 on the Noometry Index.
Last verified . 25 shared benchmarks.
MicrosoftSummary
- They share 25 benchmarks with published results for both. o3-mini 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 instruction following, where o3-mini leads 75.1 to 47.7.
- The biggest single-benchmark swing is LiveBench Coding: 82.7% for o3-mini and 15.5% for Phi 3 Mini 4k Instruct.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| o3-mini | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 36.7 | 27.9 |
| Released | 2024-12-20 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 100K | — |
| Input $ / M tokens | $1.10 | — |
| Output $ / M tokens | $4.40 | — |
| Results tracked | 51 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
o3-mini: 40.8 (#132), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | o3-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Coding | 82.7% | 15.5% |
| LMArena Coding | 1378 | 1093 |
| Aider Polyglot | 60.4% | — |
| SciCode | 39.8% | — |
| GSO | 1.3% | — |
| WeirdML | 43.7% | — |
| CadEval | 54% | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
o3-mini: 29.6 (#84), Phi 3 Mini 4k Instruct: —
| Benchmark | o3-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| Cybench | 22.5% | — |
Reasoning o3-mini leads
o3-mini: 16.3 (#305), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | o3-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 17% | 0% |
| LiveBench Reasoning | 89.6% | 26.8% |
| LMArena Hard Prompts | 1366 | 1072 |
| LiveBench Data Analysis | 70.6% | 34.7% |
| LiveBench | 75.9% | 22.4% |
| ARC-AGI-2 | 3% | — |
| SimpleBench | 22.8% | — |
| ARC-AGI-1 | 34.5% | — |
| CritPt | 0.3% | — |
| Mystery Game Puzzles | 7% | — |
| DTBench | 68.8% | — |
| LMCA | 19% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 140.34 | — |
| ForecastBench | 59.6 | — |
| HellaSwag | — | 76.7% |
| WinoGrande | — | 70.8% |
Math o3-mini leads
o3-mini: 28.1 (#244), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | o3-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Math | 77.3% | 15.7% |
| LMArena Math | 1396 | 1111 |
| FrontierMath (Tiers 1-3) | 18.6% | — |
| FrontierMath Tier 4 | 0% | — |
| OTIS Mock AIME 2024-2025 | 76.9% | — |
| MATH Level 5 | 96.5% | — |
| FrontierMath (Feb 2025 set) | 12.4% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge o3-mini leads
o3-mini: 38.3 (#146), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | o3-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1364 | 1045 |
| GPQA Diamond | 77% | — |
| SimpleQA Verified | 15.3% | — |
| Confabulations | 17.9% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual o3-mini leads
o3-mini: 45.7 (#164), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | o3-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1319 | 1021 |
| LMArena Chinese | 1379 | 1021 |
| LMArena French | 1334 | 1076 |
| LMArena German | 1303 | 1044 |
| LMArena Japanese | 1286 | 935 |
| LMArena Korean | 1314 | 905 |
| LMArena Russian | 1304 | 1022 |
| LMArena Spanish | 1321 | 1085 |
Instruction Following o3-mini leads
o3-mini: 75.1 (#72), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | o3-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Instruction Following | 84.4% | 39.1% |
| LMArena Instruction Following | 1337 | 1053 |
Long Context o3-mini leads
o3-mini: 33.8 (#256), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | o3-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1343 | 1044 |
| Fiction.LiveBench | 50% | — |
Writing & Preference o3-mini leads
o3-mini: 50.3 (#182), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | o3-mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1337 | 1073 |
| LMArena Creative Writing | 1286 | 1037 |
| LMArena Multi-Turn | 1320 | 1018 |
| LiveBench Language | 50.7% | 9.2% |
| Short-Story Creative Writing | 61.7% | — |
Frequently asked questions
Is o3-mini better than Phi 3 Mini 4k Instruct?
o3-mini is the stronger model overall, scoring 36.7 to 27.9 on the Noometry Index.
Is o3-mini or Phi 3 Mini 4k Instruct better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 26.6 in the Noometry coding category.
How many benchmarks do o3-mini and Phi 3 Mini 4k Instruct share?
25 benchmarks have published results for both models. o3-mini has 51 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.