Model comparison
Claude Sonnet 4 vs phi-3-medium 14B
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 29.7 on the Noometry Index.
Last verified . 3 shared benchmarks.
MicrosoftSummary
- They share 3 benchmarks with published results for both. Claude Sonnet 4 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 Sonnet 4 leads 41.8 to 9.1.
- The biggest single-benchmark swing is MATH Level 5: 84.4% for Claude Sonnet 4 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 Sonnet 4 | phi-3-medium 14B | |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 40.8 | 29.7 |
| Released | 2025-05-22 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 58 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 43.5 (#88), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Claude Sonnet 4 | phi-3-medium 14B |
|---|---|---|
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1414 | — |
| BigCodeBench Complete | — | 48.7% |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4: 38.5 (#31), phi-3-medium 14B: —
| Benchmark | Claude Sonnet 4 | phi-3-medium 14B |
|---|---|---|
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Not comparable
Claude Sonnet 4: 22.9 (#187), phi-3-medium 14B: —
| Benchmark | Claude Sonnet 4 | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 141.69 | 121.23 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| EnigmaEval | 3.1% | — |
| LMArena Hard Prompts | 1372 | — |
| DTBench | 77.1% | — |
| LMCA | 29% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| ForecastBench | 60.2 | — |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Claude Sonnet 4 | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | 84.4% | 17.6% |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| Omni-MATH | 60.2% | — |
| LMArena Math | 1375 | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Claude Sonnet 4 | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 79.2% | 27.6% |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
| LMArena Expert | 1372 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multimodal Not comparable
Claude Sonnet 4: 26.2 (#121), phi-3-medium 14B: —
| Benchmark | Claude Sonnet 4 | phi-3-medium 14B |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Not comparable
Claude Sonnet 4: 46.7 (#156), phi-3-medium 14B: —
| Benchmark | Claude Sonnet 4 | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1333 | — |
| LMArena Chinese | 1350 | — |
| LMArena French | 1363 | — |
| LMArena German | 1331 | — |
| LMArena Japanese | 1302 | — |
| LMArena Korean | 1291 | — |
| LMArena Russian | 1355 | — |
| LMArena Spanish | 1357 | — |
Instruction Following Not comparable
Claude Sonnet 4: 71.7 (#145), phi-3-medium 14B: —
| Benchmark | Claude Sonnet 4 | phi-3-medium 14B |
|---|---|---|
| IFEval | 84% | — |
| LMArena Instruction Following | 1376 | — |
Long Context Not comparable
Claude Sonnet 4: 33.7 (#259), phi-3-medium 14B: —
| Benchmark | Claude Sonnet 4 | phi-3-medium 14B |
|---|---|---|
| Fiction.LiveBench | 46.9% | — |
| LMArena Longer Query | 1398 | — |
Writing & Preference Not comparable
Claude Sonnet 4: 57.1 (#132), phi-3-medium 14B: —
| Benchmark | Claude Sonnet 4 | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1351 | — |
| LMArena Creative Writing | 1345 | — |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
| LMArena Multi-Turn | 1376 | — |
Frequently asked questions
Is Claude Sonnet 4 better than phi-3-medium 14B?
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 29.7 on the Noometry Index.
Is Claude Sonnet 4 or phi-3-medium 14B better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 36.8 in the Noometry coding category.
How many benchmarks do Claude Sonnet 4 and phi-3-medium 14B share?
3 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and phi-3-medium 14B has 13.