Model comparison
o1 vs phi-3-medium 14B
o1 is the stronger model overall, scoring 40.6 to 29.1 on the Noometry Index.
Last verified . 3 shared benchmarks.
MicrosoftSummary
- They share 3 benchmarks with published results for both. o1 scores higher in 3 categories and phi-3-medium 14B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o1 leads 41.5 to 9.1.
- The biggest single-benchmark swing is MATH Level 5: 94.7% for o1 and 17.6% for phi-3-medium 14B.
- phi-3-medium 14B has downloadable open weights; the other is API-only.
Side by side
| o1 | phi-3-medium 14B | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 40.6 | 29.1 |
| 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 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
o1: 45.7 (#64), phi-3-medium 14B: 36.3 (#198)
| Benchmark | o1 | phi-3-medium 14B |
|---|---|---|
| Aider Polyglot | 61.7% | — |
| WeirdML | 47.6% | — |
| BigCodeBench Instruct | — | 37.6% |
| LiveBench Coding | 69.7% | — |
| LMArena Coding | 1367 | — |
| BigCodeBench Complete | — | 48.7% |
| CadEval | 56% | — |
| HumanEval+ | 89% | — |
| MBPP+ | 80.2% | — |
Agentic & Tool Use Not comparable
o1: 24.3 (#111), phi-3-medium 14B: —
| Benchmark | o1 | phi-3-medium 14B |
|---|---|---|
| Cybench | 10% | — |
| METR Time Horizons | 51.1% | — |
Reasoning Not comparable
o1: 27.5 (#103), phi-3-medium 14B: —
| Benchmark | o1 | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 141.92 | 121.18 |
| SimpleBench | 41.7% | — |
| ARC-AGI-1 | 30.7% | — |
| Chess Puzzles | 15% | — |
| EnigmaEval | 5.7% | — |
| LiveBench Reasoning | 91.6% | — |
| LMArena Hard Prompts | 1372 | — |
| DTBench | 74.7% | — |
| LiveBench Data Analysis | 65.5% | — |
| LMCA | 22.3% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| HellaSwag | — | 82.4% |
| LiveBench | 75.7% | — |
| WinoGrande | — | 81.5% |
Math o1 leads
o1: 34.9 (#150), phi-3-medium 14B: 25.2 (#249)
| Benchmark | o1 | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | 94.7% | 17.6% |
| FrontierMath (Tiers 1-3) | 14.7% | — |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| LiveBench Math | 80.3% | — |
| LMArena Math | 1388 | — |
| FrontierMath (Feb 2025 set) | 9.3% | — |
Knowledge o1 leads
o1: 41.5 (#101), phi-3-medium 14B: 9.1 (#301)
| Benchmark | o1 | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 76.8% | 27.6% |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | 41.1% | — |
| Confabulations | 11.7% | — |
| LMArena Expert | 1362 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multimodal Not comparable
o1: 33.6 (#87), phi-3-medium 14B: —
| Benchmark | o1 | phi-3-medium 14B |
|---|---|---|
| LMArena Vision | 1168 | — |
| GeoBench | 80% | — |
| VPCT | 37% | — |
| SpatialViz-Bench | 41.4% | — |
Multilingual Not comparable
o1: 48.8 (#137), phi-3-medium 14B: —
| Benchmark | o1 | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1359 | — |
| LMArena Chinese | 1394 | — |
| LMArena French | 1343 | — |
| LMArena German | 1337 | — |
| LMArena Japanese | 1346 | — |
| LMArena Korean | 1396 | — |
| LMArena Russian | 1356 | — |
| LMArena Spanish | 1345 | — |
Instruction Following Not comparable
o1: 75.0 (#82), phi-3-medium 14B: —
| Benchmark | o1 | phi-3-medium 14B |
|---|---|---|
| LiveBench Instruction Following | 81.5% | — |
| LMArena Instruction Following | 1368 | — |
Long Context Not comparable
o1: 50.3 (#9), phi-3-medium 14B: —
| Benchmark | o1 | phi-3-medium 14B |
|---|---|---|
| Fiction.LiveBench | 83.3% | — |
| LMArena Longer Query | 1378 | — |
Writing & Preference Not comparable
o1: 55.8 (#139), phi-3-medium 14B: —
| Benchmark | o1 | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1366 | — |
| LMArena Creative Writing | 1347 | — |
| Short-Story Creative Writing | 70.2% | — |
| LMArena Multi-Turn | 1368 | — |
| LiveBench Language | 65.4% | — |
Frequently asked questions
Is o1 better than phi-3-medium 14B?
o1 is the stronger model overall, scoring 40.6 to 29.1 on the Noometry Index.
Is o1 or phi-3-medium 14B better for coding?
o1 scores higher on coding benchmarks: 45.7 versus 36.3 in the Noometry coding category.
How many benchmarks do o1 and phi-3-medium 14B share?
3 benchmarks have published results for both models. o1 has 52 scored results on Noometry and phi-3-medium 14B has 13.