Model comparison
GPT-4o mini vs Phi 3 Mini 4k Instruct
Phi 3 Mini 4k Instruct is the stronger model overall, scoring 27.9 to 25.5 on the Noometry Index.
Last verified . 28 shared benchmarks.
MicrosoftSummary
- They share 28 benchmarks with published results for both. GPT-4o mini scores higher in 4 categories and Phi 3 Mini 4k Instruct in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Phi 3 Mini 4k Instruct leads 26.6 to 10.4.
- The biggest single-benchmark swing is LiveBench Coding: 43.1% for GPT-4o mini and 15.5% for Phi 3 Mini 4k Instruct.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-4o mini | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 25.5 | 27.9 |
| Released | 2024-07-18 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 60 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi 3 Mini 4k Instruct leads
GPT-4o mini: 22.0 (#335), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | GPT-4o mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Coding | 43.1% | 15.5% |
| LMArena Coding | 1290 | 1093 |
| HumanEval+ | 83.5% | 59.1% |
| MBPP+ | 72.2% | 54.2% |
| Aider Polyglot | 3.6% | — |
| WeirdML | 11.8% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 57.4% | — |
Agentic & Tool Use Not comparable
GPT-4o mini: 27.5 (#101), Phi 3 Mini 4k Instruct: —
| Benchmark | GPT-4o mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| BALROG | 17.4% | — |
Reasoning Phi 3 Mini 4k Instruct leads
GPT-4o mini: 8.7 (#347), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | GPT-4o mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LiveBench Reasoning | 32.8% | 26.8% |
| LMArena Hard Prompts | 1267 | 1072 |
| LiveBench Data Analysis | 50% | 34.7% |
| LiveBench | 41.3% | 22.4% |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 10.7% | — |
| Kagi LLM Benchmark | 28.8% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 54.4% | — |
| LMCA | 10.4% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 126.56 | — |
| HellaSwag | — | 76.7% |
| PIQA | 88.7% | — |
| WinoGrande | — | 70.8% |
Math Phi 3 Mini 4k Instruct leads
GPT-4o mini: 10.4 (#314), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | GPT-4o mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Math | 36.3% | 15.7% |
| LMArena Math | 1267 | 1111 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.9% | — |
| Omni-MATH | 28% | — |
| MATH Level 5 | 52.6% | — |
| GSM8K | 91.3% | — |
Knowledge Phi 3 Mini 4k Instruct leads
GPT-4o mini: 17.7 (#284), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | GPT-4o mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1235 | 1045 |
| MMLU | 81.8% | 68.8% |
| GPQA Diamond | 37.7% | — |
| SimpleQA Verified | 8.3% | — |
| MMLU-Pro | 60.3% | — |
| Confabulations | 37.2% | — |
| GPQA (HELM) | 36.8% | — |
| ARC (AI2) Challenge | — | 84.9% |
| BoolQ | 88.7% | — |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multimodal Not comparable
GPT-4o mini: 25.9 (#122), Phi 3 Mini 4k Instruct: —
| Benchmark | GPT-4o mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
Multilingual GPT-4o mini leads
GPT-4o mini: 42.0 (#199), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | GPT-4o mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1266 | 1021 |
| LMArena Chinese | 1265 | 1021 |
| LMArena French | 1297 | 1076 |
| LMArena German | 1272 | 1044 |
| LMArena Japanese | 1216 | 935 |
| LMArena Korean | 1195 | 905 |
| LMArena Russian | 1275 | 1022 |
| LMArena Spanish | 1276 | 1085 |
Instruction Following GPT-4o mini leads
GPT-4o mini: 61.9 (#239), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | GPT-4o mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Instruction Following | 56.8% | 39.1% |
| LMArena Instruction Following | 1258 | 1053 |
| IFEval | 78.2% | — |
Long Context GPT-4o mini leads
GPT-4o mini: 39.1 (#186), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | GPT-4o mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1289 | 1044 |
Writing & Preference GPT-4o mini leads
GPT-4o mini: 39.5 (#248), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | GPT-4o mini | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1286 | 1073 |
| LMArena Creative Writing | 1268 | 1037 |
| LMArena Multi-Turn | 1285 | 1018 |
| LiveBench Language | 28.6% | 9.2% |
| Short-Story Creative Writing | 67.2% | — |
| EQ-Bench Creative Writing | 873 | — |
| WildBench | 79.1% | — |
Frequently asked questions
Is GPT-4o mini better than Phi 3 Mini 4k Instruct?
Phi 3 Mini 4k Instruct is the stronger model overall, scoring 27.9 to 25.5 on the Noometry Index.
Is GPT-4o mini or Phi 3 Mini 4k Instruct better for coding?
Phi 3 Mini 4k Instruct scores higher on coding benchmarks: 26.6 versus 22.0 in the Noometry coding category.
How many benchmarks do GPT-4o mini and Phi 3 Mini 4k Instruct share?
28 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.