Model comparison
GPT-4.1 vs phi-3-medium 14B
GPT-4.1 is the stronger model overall, scoring 35.9 to 29.7 on the Noometry Index.
Last verified . 3 shared benchmarks.
MicrosoftSummary
- They share 3 benchmarks with published results for both. GPT-4.1 scores higher in 1 category and phi-3-medium 14B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-4.1 leads 37.1 to 9.1.
- The biggest single-benchmark swing is MATH Level 5: 83% for GPT-4.1 and 17.6% for phi-3-medium 14B.
- phi-3-medium 14B has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 | phi-3-medium 14B | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 35.9 | 29.7 |
| 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 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
GPT-4.1: 34.4 (#238), phi-3-medium 14B: 36.8 (#201)
| Benchmark | GPT-4.1 | phi-3-medium 14B |
|---|---|---|
| SWE-bench Verified | 48.5% | — |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| WeirdML | 39% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1391 | — |
| BigCodeBench Complete | — | 48.7% |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |
Agentic & Tool Use Not comparable
GPT-4.1: 34.7 (#43), phi-3-medium 14B: —
| Benchmark | GPT-4.1 | phi-3-medium 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 54% | — |
Reasoning Not comparable
GPT-4.1: 11.7 (#339), phi-3-medium 14B: —
| Benchmark | GPT-4.1 | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 136.78 | 121.23 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | 27% | — |
| Kagi LLM Benchmark | 52.3% | — |
| ARC-AGI-1 | 5.5% | — |
| Chess Puzzles | 6% | — |
| EnigmaEval | 2.2% | — |
| LMArena Hard Prompts | 1384 | — |
| DTBench | 68.3% | — |
| LMCA | 25.6% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| ForecastBench | 61.5 | — |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math phi-3-medium 14B leads
GPT-4.1: 22.3 (#280), phi-3-medium 14B: 27.3 (#250)
| Benchmark | GPT-4.1 | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | 83% | 17.6% |
| FrontierMath (Tiers 1-3) | 6% | — |
| OTIS Mock AIME 2024-2025 | 38.3% | — |
| Omni-MATH | 47.1% | — |
| LMArena Math | 1370 | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GPT-4.1 leads
GPT-4.1: 37.1 (#160), phi-3-medium 14B: 9.1 (#306)
| Benchmark | GPT-4.1 | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 66.9% | 27.6% |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | 31.1% | — |
| MMLU-Pro | 81.1% | — |
| Vectara Hallucination Rate | 5.6% | — |
| GPQA (HELM) | 65.9% | — |
| LMArena Expert | 1364 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multimodal Not comparable
GPT-4.1: 38.2 (#67), phi-3-medium 14B: —
| Benchmark | GPT-4.1 | phi-3-medium 14B |
|---|---|---|
| LMArena Vision | 1211 | — |
| GeoBench | 72% | — |
Multilingual Not comparable
GPT-4.1: 49.4 (#133), phi-3-medium 14B: —
| Benchmark | GPT-4.1 | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1370 | — |
| LMArena Chinese | 1382 | — |
| LMArena French | 1382 | — |
| LMArena German | 1381 | — |
| LMArena Japanese | 1319 | — |
| LMArena Korean | 1339 | — |
| LMArena Russian | 1377 | — |
| LMArena Spanish | 1376 | — |
Instruction Following Not comparable
GPT-4.1: 71.3 (#153), phi-3-medium 14B: —
| Benchmark | GPT-4.1 | phi-3-medium 14B |
|---|---|---|
| IFEval | 83.8% | — |
| LMArena Instruction Following | 1367 | — |
Long Context Not comparable
GPT-4.1: 40.0 (#163), phi-3-medium 14B: —
| Benchmark | GPT-4.1 | phi-3-medium 14B |
|---|---|---|
| Fiction.LiveBench | 63.9% | — |
| LMArena Longer Query | 1385 | — |
Writing & Preference Not comparable
GPT-4.1: 57.6 (#125), phi-3-medium 14B: —
| Benchmark | GPT-4.1 | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1383 | — |
| LMArena Creative Writing | 1363 | — |
| EQ-Bench Creative Writing | 1420 | — |
| WildBench | 85.4% | — |
| LMArena Multi-Turn | 1398 | — |
Frequently asked questions
Is GPT-4.1 better than phi-3-medium 14B?
GPT-4.1 is the stronger model overall, scoring 35.9 to 29.7 on the Noometry Index.
Is GPT-4.1 or phi-3-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 34.4 in the Noometry coding category.
How many benchmarks do GPT-4.1 and phi-3-medium 14B share?
3 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and phi-3-medium 14B has 13.