Model comparison
GPT-5.2 Pro vs Phi 3 Mini 128k Instruct
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 29.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in math, where GPT-5.2 Pro leads 65.3 to 31.6.
- Phi 3 Mini 128k Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5.2 Pro | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 52.3 | 29.7 |
| Released | 2025-12-11 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $21 | — |
| Output $ / M tokens | $168 | — |
| Results tracked | 8 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.2 Pro: —, Phi 3 Mini 128k Instruct: 28.8 (#312)
| Benchmark | GPT-5.2 Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| BigCodeBench Instruct | — | 29.6% |
| LMArena Coding | — | 1039 |
| BigCodeBench Complete | — | 40.6% |
Reasoning GPT-5.2 Pro leads
GPT-5.2 Pro: 51.5 (#33), Phi 3 Mini 128k Instruct: 19.6 (#256)
| Benchmark | GPT-5.2 Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| ARC-AGI-2 | 54.2% | — |
| SimpleBench | 57.4% | — |
| NYT Connections (extended) | 79.3% | — |
| ARC-AGI-1 | 90.5% | — |
| LMArena Hard Prompts | — | 1028 |
| Epoch Capabilities Index | 155.4 | — |
Math GPT-5.2 Pro leads
GPT-5.2 Pro: 65.3 (#29), Phi 3 Mini 128k Instruct: 31.6 (#222)
| Benchmark | GPT-5.2 Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | — |
| FrontierMath Tier 4 | 46% | — |
| LMArena Math | — | 1089 |
| FrontierMath Tier 4 (v1) | 31.3% | — |
Knowledge Not comparable
GPT-5.2 Pro: —, Phi 3 Mini 128k Instruct: 26.8 (#254)
| Benchmark | GPT-5.2 Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | — | 984 |
Multilingual Not comparable
GPT-5.2 Pro: —, Phi 3 Mini 128k Instruct: 25.2 (#285)
| Benchmark | GPT-5.2 Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | — | 1000 |
| LMArena Chinese | — | 1016 |
| LMArena French | — | 1039 |
| LMArena German | — | 1006 |
| LMArena Japanese | — | 899 |
| LMArena Korean | — | 856 |
| LMArena Russian | — | 1004 |
| LMArena Spanish | — | 1059 |
Instruction Following Not comparable
GPT-5.2 Pro: —, Phi 3 Mini 128k Instruct: 51.8 (#294)
| Benchmark | GPT-5.2 Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1023 |
Long Context Not comparable
GPT-5.2 Pro: —, Phi 3 Mini 128k Instruct: 30.4 (#289)
| Benchmark | GPT-5.2 Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | — | 996 |
Writing & Preference Not comparable
GPT-5.2 Pro: —, Phi 3 Mini 128k Instruct: 27.1 (#301)
| Benchmark | GPT-5.2 Pro | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | — | 1050 |
| LMArena Creative Writing | — | 1024 |
| LMArena Multi-Turn | — | 989 |
Frequently asked questions
Is GPT-5.2 Pro better than Phi 3 Mini 128k Instruct?
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 29.7 on the Noometry Index.
How many benchmarks do GPT-5.2 Pro and Phi 3 Mini 128k Instruct share?
0 benchmarks have published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.