Model comparison
GPT-4.1 vs Phi 3 Mini 4k Instruct
GPT-4.1 is the stronger model overall, scoring 35.7 to 27.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
MicrosoftSummary
- They share 18 benchmarks with published results for both. GPT-4.1 scores higher in 6 categories and Phi 3 Mini 4k Instruct in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4.1 leads 57.8 to 27.7.
- The biggest single-benchmark swing is Chess Puzzles: 6% for GPT-4.1 and 0% for Phi 3 Mini 4k Instruct.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 35.7 | 27.4 |
| Released | 2025-04-14 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 33K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $8 | — |
| Results tracked | 52 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.1 leads
GPT-4.1: 34.2 (#228), Phi 3 Mini 4k Instruct: 26.1 (#319)
| Benchmark | GPT-4.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1391 | 1093 |
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| WeirdML | 39% | — |
| LiveBench Coding | — | 15.5% |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
GPT-4.1: 34.4 (#40), Phi 3 Mini 4k Instruct: —
| Benchmark | GPT-4.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
Reasoning Phi 3 Mini 4k Instruct leads
GPT-4.1: 11.7 (#334), Phi 3 Mini 4k Instruct: 13.6 (#326)
| Benchmark | GPT-4.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 6% | 0% |
| LMArena Hard Prompts | 1384 | 1072 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| Kagi LLM Benchmark | 52.3% | — |
| ARC-AGI-1 | 5.5% | — |
| EnigmaEval | 2.2% | — |
| LiveBench Reasoning | — | 26.8% |
| DTBench | 68.3% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 25.6% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 136.79 | — |
| ForecastBench | 61.5 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Phi 3 Mini 4k Instruct leads
GPT-4.1: 21.4 (#269), Phi 3 Mini 4k Instruct: 24.5 (#258)
| Benchmark | GPT-4.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1369 | 1111 |
| FrontierMath (Tiers 1-3) | 6% | — |
| OTIS Mock AIME 2024-2025 | 38.3% | — |
| Omni-MATH | 47.1% | — |
| LiveBench Math | — | 15.7% |
| MATH Level 5 | 83% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GPT-4.1 leads
GPT-4.1: 37.0 (#152), Phi 3 Mini 4k Instruct: 27.9 (#241)
| Benchmark | GPT-4.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1364 | 1045 |
| GPQA Diamond | 66.9% | — |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| Vectara Hallucination Rate | 5.6% | — |
| GPQA (HELM) | 65.9% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multimodal Not comparable
GPT-4.1: 37.5 (#66), Phi 3 Mini 4k Instruct: —
| Benchmark | GPT-4.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1210 | — |
| GeoBench | 72% | — |
Multilingual GPT-4.1 leads
GPT-4.1: 49.6 (#128), Phi 3 Mini 4k Instruct: 26.5 (#275)
| Benchmark | GPT-4.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1370 | 1021 |
| LMArena Chinese | 1382 | 1021 |
| LMArena French | 1383 | 1075 |
| LMArena German | 1380 | 1044 |
| LMArena Japanese | 1320 | 935 |
| LMArena Korean | 1339 | 905 |
| LMArena Russian | 1377 | 1022 |
| LMArena Spanish | 1375 | 1084 |
Instruction Following GPT-4.1 leads
GPT-4.1: 71.5 (#148), Phi 3 Mini 4k Instruct: 48.0 (#298)
| Benchmark | GPT-4.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1367 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
| IFEval | 83.8% | — |
Long Context GPT-4.1 leads
GPT-4.1: 40.0 (#158), Phi 3 Mini 4k Instruct: 31.7 (#271)
| Benchmark | GPT-4.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1385 | 1044 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference GPT-4.1 leads
GPT-4.1: 57.8 (#120), Phi 3 Mini 4k Instruct: 27.7 (#295)
| Benchmark | GPT-4.1 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1383 | 1073 |
| LMArena Creative Writing | 1363 | 1037 |
| LMArena Multi-Turn | 1398 | 1018 |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is GPT-4.1 better than Phi 3 Mini 4k Instruct?
GPT-4.1 is the stronger model overall, scoring 35.7 to 27.4 on the Noometry Index.
Is GPT-4.1 or Phi 3 Mini 4k Instruct better for coding?
GPT-4.1 scores higher on coding benchmarks: 34.2 versus 26.1 in the Noometry coding category.
How many benchmarks do GPT-4.1 and Phi 3 Mini 4k Instruct share?
18 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.