Model comparison
o3-mini vs Phi 3 Small 8k Instruct
o3-mini is the stronger model overall, scoring 36.7 to 28.8 on the Noometry Index.
Last verified . 24 shared benchmarks.
MicrosoftSummary
- They share 24 benchmarks with published results for both. o3-mini scores higher in 8 categories and Phi 3 Small 8k Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where o3-mini leads 75.3 to 52.2.
- The biggest single-benchmark swing is LiveBench Reasoning: 89.6% for o3-mini and 15.9% for Phi 3 Small 8k Instruct.
- Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.
Side by side
| o3-mini | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 36.7 | 28.8 |
| 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 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
o3-mini: 41.4 (#116), Phi 3 Small 8k Instruct: 27.4 (#313)
| Benchmark | o3-mini | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Coding | 82.7% | 20.3% |
| LMArena Coding | 1378 | 1102 |
| Aider Polyglot | 60.4% | — |
| SciCode | 39.8% | — |
| GSO | 1.3% | — |
| WeirdML | 43.7% | — |
| CadEval | 54% | — |
Agentic & Tool Use Not comparable
o3-mini: 29.3 (#79), Phi 3 Small 8k Instruct: —
| Benchmark | o3-mini | Phi 3 Small 8k Instruct |
|---|---|---|
| Cybench | 22.5% | — |
Reasoning o3-mini leads
o3-mini: 16.3 (#295), Phi 3 Small 8k Instruct: 14.2 (#319)
| Benchmark | o3-mini | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Reasoning | 89.6% | 15.9% |
| LMArena Hard Prompts | 1366 | 1100 |
| LiveBench Data Analysis | 70.6% | 30.3% |
| LiveBench | 75.9% | 24% |
| ARC-AGI-2 | 3% | — |
| SimpleBench | 22.8% | — |
| ARC-AGI-1 | 34.5% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | 17% | — |
| Mystery Game Puzzles | 7% | — |
| DTBench | 68.8% | — |
| LMCA | 19% | — |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 140.35 | — |
| ForecastBench | 59.6 | — |
| HellaSwag | — | 77% |
| WinoGrande | — | 81.5% |
Math o3-mini leads
o3-mini: 27.6 (#236), Phi 3 Small 8k Instruct: 25.4 (#247)
| Benchmark | o3-mini | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Math | 77.3% | 17.6% |
| LMArena Math | 1396 | 1151 |
| 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 (#135), Phi 3 Small 8k Instruct: 28.5 (#237)
| Benchmark | o3-mini | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1364 | 1067 |
| GPQA Diamond | 77% | — |
| SimpleQA Verified | 15.3% | — |
| Confabulations | 17.9% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multilingual o3-mini leads
o3-mini: 45.9 (#159), Phi 3 Small 8k Instruct: 28.6 (#267)
| Benchmark | o3-mini | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1319 | 1058 |
| LMArena Chinese | 1379 | 1061 |
| LMArena French | 1333 | 1134 |
| LMArena German | 1303 | 1080 |
| LMArena Japanese | 1286 | 966 |
| LMArena Korean | 1314 | 894 |
| LMArena Russian | 1304 | 1111 |
| LMArena Spanish | 1321 | 1111 |
Instruction Following o3-mini leads
o3-mini: 75.3 (#67), Phi 3 Small 8k Instruct: 52.2 (#287)
| Benchmark | o3-mini | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Instruction Following | 84.4% | 47.2% |
| LMArena Instruction Following | 1338 | 1087 |
Long Context Too close to call
o3-mini: 33.8 (#251), Phi 3 Small 8k Instruct: 33.0 (#262)
| Benchmark | o3-mini | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1343 | 1088 |
| Fiction.LiveBench | 50% | — |
Writing & Preference o3-mini leads
o3-mini: 50.4 (#177), Phi 3 Small 8k Instruct: 31.3 (#279)
| Benchmark | o3-mini | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1337 | 1110 |
| LMArena Creative Writing | 1286 | 1083 |
| LMArena Multi-Turn | 1320 | 1068 |
| LiveBench Language | 50.7% | 12.9% |
| Short-Story Creative Writing | 61.7% | — |
Frequently asked questions
Is o3-mini better than Phi 3 Small 8k Instruct?
o3-mini is the stronger model overall, scoring 36.7 to 28.8 on the Noometry Index.
Is o3-mini or Phi 3 Small 8k Instruct better for coding?
o3-mini scores higher on coding benchmarks: 41.4 versus 27.4 in the Noometry coding category.
How many benchmarks do o3-mini and Phi 3 Small 8k Instruct share?
24 benchmarks have published results for both models. o3-mini has 51 scored results on Noometry and Phi 3 Small 8k Instruct has 32.