Model comparison
Claude Sonnet 5 vs phi-3-medium 14B
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 29.7 on the Noometry Index.
Last verified . 2 shared benchmarks.
MicrosoftSummary
- They share 2 benchmarks with published results for both. Claude Sonnet 5 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 5 leads 55.6 to 9.1.
- The biggest single-benchmark swing is GPQA Diamond: 90.5% for Claude Sonnet 5 and 27.6% for phi-3-medium 14B.
- phi-3-medium 14B has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 5 | phi-3-medium 14B | |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 54.6 | 29.7 |
| Released | 2026-06-29 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 51 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#26), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Claude Sonnet 5 | phi-3-medium 14B |
|---|---|---|
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1541 | — |
| SciCode | 54.3% | — |
| GSO | 37.3% | — |
| WeirdML | 68.8% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1483 | — |
| BigCodeBench Complete | — | 48.7% |
| ALE-Bench | 1,463 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 5: 42.8 (#18), phi-3-medium 14B: —
| Benchmark | Claude Sonnet 5 | phi-3-medium 14B |
|---|---|---|
| APEX-Agents | 54.5% | — |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |
Reasoning Not comparable
Claude Sonnet 5: 49.1 (#39), phi-3-medium 14B: —
| Benchmark | Claude Sonnet 5 | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 156.21 | 121.23 |
| SimpleBench | 60.6% | — |
| NYT Connections (extended) | 75.1% | — |
| CritPt | 16.9% | — |
| Chess Puzzles | 35% | — |
| LMArena Hard Prompts | 1461 | — |
| Mystery Game Puzzles | 35% | — |
| DTBench | 92.5% | — |
| LMCA | 50% | — |
| Surface Evolver Bench | 60% | — |
| Adversarial NLI | — | 55.8% |
| Bench to the Future 3 | 0.14 | — |
| BIG-Bench Hard | — | 81.4% |
| ForecastBench | 61.1 | — |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.2 (#27), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Claude Sonnet 5 | phi-3-medium 14B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 94.7% | — |
| ProofBench | 77% | — |
| LMArena Math | 1467 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Claude Sonnet 5 leads
Claude Sonnet 5: 55.6 (#47), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Claude Sonnet 5 | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 90.5% | 27.6% |
| SimpleQA Verified | 33.7% | — |
| LMArena Expert | 1490 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multimodal Not comparable
Claude Sonnet 5: 42.4 (#31), phi-3-medium 14B: —
| Benchmark | Claude Sonnet 5 | phi-3-medium 14B |
|---|---|---|
| LMArena Vision | 1274 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual Not comparable
Claude Sonnet 5: 53.8 (#55), phi-3-medium 14B: —
| Benchmark | Claude Sonnet 5 | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1431 | — |
| LMArena Chinese | 1477 | — |
| LMArena French | 1460 | — |
| LMArena German | 1440 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1411 | — |
| LMArena Russian | 1451 | — |
| LMArena Spanish | 1437 | — |
Instruction Following Not comparable
Claude Sonnet 5: 76.3 (#41), phi-3-medium 14B: —
| Benchmark | Claude Sonnet 5 | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1452 | — |
Long Context Not comparable
Claude Sonnet 5: 44.8 (#55), phi-3-medium 14B: —
| Benchmark | Claude Sonnet 5 | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1463 | — |
Writing & Preference Not comparable
Claude Sonnet 5: 69.2 (#25), phi-3-medium 14B: —
| Benchmark | Claude Sonnet 5 | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1442 | — |
| LMArena Creative Writing | 1416 | — |
| EQ-Bench Creative Writing | 1794 | — |
| EQ-Bench 4 | 1236 | — |
| LMArena Multi-Turn | 1454 | — |
Frequently asked questions
Is Claude Sonnet 5 better than phi-3-medium 14B?
Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 29.7 on the Noometry Index.
Is Claude Sonnet 5 or phi-3-medium 14B better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 36.8 in the Noometry coding category.
How many benchmarks do Claude Sonnet 5 and phi-3-medium 14B share?
2 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and phi-3-medium 14B has 13.