Model comparison
Claude 3.7 Sonnet vs phi-3-medium 14B
Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 29.1 on the Noometry Index.
Last verified . 3 shared benchmarks.
MicrosoftSummary
- They share 3 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 3 categories and phi-3-medium 14B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude 3.7 Sonnet leads 39.7 to 9.1.
- The biggest single-benchmark swing is MATH Level 5: 91.2% for Claude 3.7 Sonnet and 17.6% for phi-3-medium 14B.
- phi-3-medium 14B has downloadable open weights; the other is API-only.
Side by side
| Claude 3.7 Sonnet | phi-3-medium 14B | |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 39.4 | 29.1 |
| Released | 2025-02-24 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 58 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 41.1 (#120), phi-3-medium 14B: 36.3 (#198)
| Benchmark | Claude 3.7 Sonnet | phi-3-medium 14B |
|---|---|---|
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| GSO | 3.8% | — |
| BigCodeBench Instruct | — | 37.6% |
| LiveBench Coding | 74.5% | — |
| LMArena Coding | 1361 | — |
| BigCodeBench Complete | — | 48.7% |
| CadEval | 54% | — |
Agentic & Tool Use Not comparable
Claude 3.7 Sonnet: 33.9 (#46), phi-3-medium 14B: —
| Benchmark | Claude 3.7 Sonnet | phi-3-medium 14B |
|---|---|---|
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
Reasoning Not comparable
Claude 3.7 Sonnet: 18.7 (#252), phi-3-medium 14B: —
| Benchmark | Claude 3.7 Sonnet | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 141.16 | 121.18 |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| ARC-AGI-1 | 28.6% | — |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| LMArena Hard Prompts | 1333 | — |
| LiveBench Data Analysis | 74% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| ForecastBench | 61.8 | — |
| HellaSwag | — | 82.4% |
| LiveBench | 76.1% | — |
| WinoGrande | — | 81.5% |
Math Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 35.7 (#137), phi-3-medium 14B: 25.2 (#249)
| Benchmark | Claude 3.7 Sonnet | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | 91.2% | 17.6% |
| OTIS Mock AIME 2024-2025 | 57.8% | — |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| LMArena Math | 1336 | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 39.7 (#117), phi-3-medium 14B: 9.1 (#301)
| Benchmark | Claude 3.7 Sonnet | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 79.7% | 27.6% |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |
| LMArena Expert | 1321 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multimodal Not comparable
Claude 3.7 Sonnet: 33.1 (#90), phi-3-medium 14B: —
| Benchmark | Claude 3.7 Sonnet | phi-3-medium 14B |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Not comparable
Claude 3.7 Sonnet: 44.3 (#174), phi-3-medium 14B: —
| Benchmark | Claude 3.7 Sonnet | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1296 | — |
| LMArena Chinese | 1299 | — |
| LMArena French | 1302 | — |
| LMArena German | 1301 | — |
| LMArena Japanese | 1268 | — |
| LMArena Korean | 1249 | — |
| LMArena Russian | 1311 | — |
| LMArena Spanish | 1299 | — |
Instruction Following Not comparable
Claude 3.7 Sonnet: 73.1 (#120), phi-3-medium 14B: —
| Benchmark | Claude 3.7 Sonnet | phi-3-medium 14B |
|---|---|---|
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
| LMArena Instruction Following | 1352 | — |
Long Context Not comparable
Claude 3.7 Sonnet: 50.2 (#10), phi-3-medium 14B: —
| Benchmark | Claude 3.7 Sonnet | phi-3-medium 14B |
|---|---|---|
| Fiction.LiveBench | 83.3% | — |
| LMArena Longer Query | 1373 | — |
Writing & Preference Not comparable
Claude 3.7 Sonnet: 54.6 (#145), phi-3-medium 14B: —
| Benchmark | Claude 3.7 Sonnet | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1314 | — |
| LMArena Creative Writing | 1332 | — |
| Short-Story Creative Writing | 81.1% | — |
| EQ-Bench Creative Writing | 1412 | — |
| WildBench | 81.4% | — |
| LMArena Multi-Turn | 1339 | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than phi-3-medium 14B?
Claude 3.7 Sonnet is the stronger model overall, scoring 39.4 to 29.1 on the Noometry Index.
Is Claude 3.7 Sonnet or phi-3-medium 14B better for coding?
Claude 3.7 Sonnet scores higher on coding benchmarks: 41.1 versus 36.3 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and phi-3-medium 14B share?
3 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and phi-3-medium 14B has 13.