Model comparison
o1 vs Phi 3 Small 8k Instruct
o1 is the stronger model overall, scoring 40.9 to 29.3 on the Noometry Index.
Last verified . 24 shared benchmarks.
MicrosoftSummary
- They share 24 benchmarks with published results for both. o1 scores higher in 8 categories and Phi 3 Small 8k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where o1 leads 55.6 to 31.1.
- The biggest single-benchmark swing is LiveBench Reasoning: 91.6% for o1 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
| o1 | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 40.9 | 29.3 |
| 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 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1 leads
o1: 46.1 (#70), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | o1 | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Coding | 69.7% | 20.3% |
| LMArena Coding | 1367 | 1101 |
| Aider Polyglot | 61.7% | — |
| WeirdML | 47.6% | — |
| CadEval | 56% | — |
| HumanEval+ | 89% | — |
| MBPP+ | 80.2% | — |
Agentic & Tool Use Not comparable
o1: 24.6 (#117), Phi 3 Small 8k Instruct: —
| Benchmark | o1 | Phi 3 Small 8k Instruct |
|---|---|---|
| Cybench | 10% | — |
| METR Time Horizons | 51.1% | — |
Reasoning o1 leads
o1: 27.9 (#111), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | o1 | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Reasoning | 91.6% | 15.9% |
| LMArena Hard Prompts | 1371 | 1100 |
| LiveBench Data Analysis | 65.5% | 30.3% |
| LiveBench | 75.7% | 24% |
| SimpleBench | 41.7% | — |
| ARC-AGI-1 | 30.7% | — |
| Chess Puzzles | 15% | — |
| EnigmaEval | 5.7% | — |
| DTBench | 74.7% | — |
| LMCA | 22.3% | — |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 141.91 | — |
| HellaSwag | — | 77% |
| WinoGrande | — | 81.5% |
Math o1 leads
o1: 36.1 (#175), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | o1 | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Math | 80.3% | 17.6% |
| LMArena Math | 1388 | 1151 |
| 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 Small 8k Instruct: 29.1 (#240)
| Benchmark | o1 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1361 | 1067 |
| GPQA Diamond | 76.8% | — |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | 41.1% | — |
| Confabulations | 11.7% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multimodal Not comparable
o1: 34.2 (#93), Phi 3 Small 8k Instruct: —
| Benchmark | o1 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Vision | 1168 | — |
| GeoBench | 80% | — |
| VPCT | 37% | — |
| SpatialViz-Bench | 41.4% | — |
Multilingual o1 leads
o1: 48.6 (#142), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | o1 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1358 | 1058 |
| LMArena Chinese | 1394 | 1061 |
| LMArena French | 1344 | 1135 |
| LMArena German | 1337 | 1080 |
| LMArena Japanese | 1346 | 966 |
| LMArena Korean | 1396 | 894 |
| LMArena Russian | 1356 | 1111 |
| LMArena Spanish | 1345 | 1111 |
Instruction Following o1 leads
o1: 74.8 (#86), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | o1 | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Instruction Following | 81.5% | 47.2% |
| LMArena Instruction Following | 1367 | 1087 |
Long Context o1 leads
o1: 50.3 (#9), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | o1 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1378 | 1088 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference o1 leads
o1: 55.6 (#144), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | o1 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1366 | 1110 |
| LMArena Creative Writing | 1348 | 1083 |
| LMArena Multi-Turn | 1369 | 1068 |
| LiveBench Language | 65.4% | 12.9% |
| Short-Story Creative Writing | 70.2% | — |
Frequently asked questions
Is o1 better than Phi 3 Small 8k Instruct?
o1 is the stronger model overall, scoring 40.9 to 29.3 on the Noometry Index.
Is o1 or Phi 3 Small 8k Instruct better for coding?
o1 scores higher on coding benchmarks: 46.1 versus 27.9 in the Noometry coding category.
How many benchmarks do o1 and Phi 3 Small 8k Instruct share?
24 benchmarks have published results for both models. o1 has 52 scored results on Noometry and Phi 3 Small 8k Instruct has 32.