Model comparison
GPT-5 Nano vs phi-3-medium 14B
GPT-5 Nano is the stronger model overall, scoring 33.5 to 29.7 on the Noometry Index.
Last verified . 3 shared benchmarks.
MicrosoftSummary
- They share 3 benchmarks with published results for both. GPT-5 Nano scores higher in 2 categories and phi-3-medium 14B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5 Nano leads 35.9 to 9.1.
- The biggest single-benchmark swing is MATH Level 5: 95.2% for GPT-5 Nano 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-5 Nano | phi-3-medium 14B | |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 33.5 | 29.7 |
| Released | 2025-08-07 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 49 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
GPT-5 Nano: 33.6 (#254), phi-3-medium 14B: 36.8 (#201)
| Benchmark | GPT-5 Nano | phi-3-medium 14B |
|---|---|---|
| SWE-bench Verified (bash only) | 34.8% | — |
| WeirdML | 38.1% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1351 | — |
| BigCodeBench Complete | — | 48.7% |
| ALE-Bench | 718.67 | — |
Agentic & Tool Use Not comparable
GPT-5 Nano: 25.8 (#106), phi-3-medium 14B: —
| Benchmark | GPT-5 Nano | phi-3-medium 14B |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
Reasoning Not comparable
GPT-5 Nano: 16.3 (#306), phi-3-medium 14B: —
| Benchmark | GPT-5 Nano | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 139.38 | 121.23 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| Chess Puzzles | 27% | — |
| LMArena Hard Prompts | 1328 | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 62.7% | — |
| LMCA | 7.9% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| ForecastBench | 59.1 | — |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math GPT-5 Nano leads
GPT-5 Nano: 29.4 (#241), phi-3-medium 14B: 27.3 (#250)
| Benchmark | GPT-5 Nano | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | 95.2% | 17.6% |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 81.1% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| LMArena Math | 1317 | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5 Nano leads
GPT-5 Nano: 35.9 (#178), phi-3-medium 14B: 9.1 (#306)
| Benchmark | GPT-5 Nano | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 69.4% | 27.6% |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
| LMArena Expert | 1321 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multimodal Not comparable
GPT-5 Nano: 31.3 (#108), phi-3-medium 14B: —
| Benchmark | GPT-5 Nano | phi-3-medium 14B |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual Not comparable
GPT-5 Nano: 45.3 (#172), phi-3-medium 14B: —
| Benchmark | GPT-5 Nano | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1313 | — |
| LMArena Chinese | 1356 | — |
| LMArena German | 1327 | — |
| LMArena Japanese | 1226 | — |
| LMArena Korean | 1269 | — |
| LMArena Russian | 1296 | — |
| LMArena Spanish | 1360 | — |
Instruction Following Not comparable
GPT-5 Nano: 75.0 (#79), phi-3-medium 14B: —
| Benchmark | GPT-5 Nano | phi-3-medium 14B |
|---|---|---|
| IFEval | 93.2% | — |
| LMArena Instruction Following | 1306 | — |
Long Context Not comparable
GPT-5 Nano: 31.3 (#281), phi-3-medium 14B: —
| Benchmark | GPT-5 Nano | phi-3-medium 14B |
|---|---|---|
| Fiction.LiveBench | 44.4% | — |
| LMArena Longer Query | 1312 | — |
Writing & Preference Not comparable
GPT-5 Nano: 39.1 (#249), phi-3-medium 14B: —
| Benchmark | GPT-5 Nano | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1320 | — |
| LMArena Creative Writing | 1249 | — |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
| LMArena Multi-Turn | 1311 | — |
Frequently asked questions
Is GPT-5 Nano better than phi-3-medium 14B?
GPT-5 Nano is the stronger model overall, scoring 33.5 to 29.7 on the Noometry Index.
Is GPT-5 Nano or phi-3-medium 14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 33.6 in the Noometry coding category.
How many benchmarks do GPT-5 Nano and phi-3-medium 14B share?
3 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and phi-3-medium 14B has 13.