Model comparison
o3-pro vs Phi-4
o3-pro is the stronger model overall, scoring 42.9 to 31.2 on the Noometry Index. Phi-4 costs 400× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
MicrosoftSummary
- They share 4 benchmarks with published results for both. o3-pro scores higher in 4 categories and Phi-4 in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 36.9.
- The biggest single-benchmark swing is Short-Story Creative Writing: 84.4% for o3-pro and 62.6% for Phi-4.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $20 / $80 for o3-pro.
- o3-pro accepts more context: 200K tokens versus 128K.
- Phi-4 has downloadable open weights; the other is API-only.
Side by side
| o3-pro | Phi-4 | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 42.9 | 31.2 |
| Released | 2025-06-10 | 2024-12-11 |
| Weights | Proprietary | Open |
| Context window | 200K | 128K |
| Max output | 100K | 4K |
| Input $ / M tokens | $20 | $0.07 |
| Output $ / M tokens | $80 | $0.14 |
| Results tracked | 12 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
o3-pro: 55.5 (#24), Phi-4: 34.4 (#239)
| Benchmark | o3-pro | Phi-4 |
|---|---|---|
| Aider Polyglot | 84.9% | — |
| WeirdML | 58.2% | — |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| LMArena Coding | — | 1231 |
| BigCodeBench Complete | — | 55.4% |
Agentic & Tool Use Not comparable
o3-pro: —, Phi-4: 22.8 (#128)
| Benchmark | o3-pro | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |
Reasoning o3-pro leads
o3-pro: 23.8 (#171), Phi-4: 17.7 (#291)
| Benchmark | o3-pro | Phi-4 |
|---|---|---|
| Epoch Capabilities Index | 147.42 | 130.42 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 72.1% | — |
| ARC-AGI-1 | 59.3% | — |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| LMArena Hard Prompts | — | 1220 |
| DTBench | 86.9% | — |
| LiveBench Data Analysis | — | 45.2% |
| LMCA | 38.5% | — |
| LiveBench | — | 41.6% |
Math Not comparable
o3-pro: —, Phi-4: 20.8 (#285)
| Benchmark | o3-pro | Phi-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| LiveBench Math | — | 42% |
| LMArena Math | — | 1246 |
| MATH Level 5 | — | 64.9% |
Knowledge Phi-4 leads
o3-pro: 29.5 (#238), Phi-4: 32.6 (#209)
| Benchmark | o3-pro | Phi-4 |
|---|---|---|
| Confabulations | 14.2% | 29.4% |
| Vectara Hallucination Rate | 23.3% | 3.7% |
| GPQA Diamond | — | 56.1% |
| LMArena Expert | — | 1203 |
| MMLU | — | 84.8% |
Multilingual Not comparable
o3-pro: —, Phi-4: 37.2 (#237)
| Benchmark | o3-pro | Phi-4 |
|---|---|---|
| LMArena Non-English | — | 1197 |
| LMArena Chinese | — | 1212 |
| LMArena French | — | 1224 |
| LMArena German | — | 1222 |
| LMArena Japanese | — | 1158 |
| LMArena Korean | — | 1151 |
| LMArena Russian | — | 1209 |
| LMArena Spanish | — | 1234 |
Instruction Following Not comparable
o3-pro: —, Phi-4: 60.4 (#251)
| Benchmark | o3-pro | Phi-4 |
|---|---|---|
| LiveBench Instruction Following | — | 58.4% |
| LMArena Instruction Following | — | 1201 |
Long Context o3-pro leads
o3-pro: 72.2 (#1), Phi-4: 36.9 (#226)
| Benchmark | o3-pro | Phi-4 |
|---|---|---|
| Fiction.LiveBench | 97.2% | — |
| LMArena Longer Query | — | 1217 |
Writing & Preference o3-pro leads
o3-pro: 57.1 (#133), Phi-4: 40.5 (#244)
| Benchmark | o3-pro | Phi-4 |
|---|---|---|
| Short-Story Creative Writing | 84.4% | 62.6% |
| LMArena Text | — | 1217 |
| LMArena Creative Writing | — | 1182 |
| LMArena Multi-Turn | — | 1206 |
| LiveBench Language | — | 25.6% |
Frequently asked questions
Is o3-pro better than Phi-4?
o3-pro is the stronger model overall, scoring 42.9 to 31.2 on the Noometry Index. Phi-4 costs 400× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Which is cheaper, o3-pro or Phi-4?
Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; o3-pro lists at $20 and $80.
Is o3-pro or Phi-4 better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
o3-pro does, with 200K tokens against 128K.
How many benchmarks do o3-pro and Phi-4 share?
4 benchmarks have published results for both models. o3-pro has 12 scored results on Noometry and Phi-4 has 37.