Model comparison
Claude Sonnet 4 vs Phi 3 Small 8k Instruct
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 29.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
MicrosoftSummary
- They share 17 benchmarks with published results for both. Claude Sonnet 4 scores higher in 8 categories and Phi 3 Small 8k Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Sonnet 4 leads 57.1 to 31.1.
- Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | Anthropic | Microsoft |
| Noometry Index | 40.8 | 29.3 |
| 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 | 32 |
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 Small 8k Instruct: 27.9 (#318)
| Benchmark | Claude Sonnet 4 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1414 | 1101 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
| LiveBench Coding | — | 20.3% |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4: 38.5 (#31), Phi 3 Small 8k Instruct: —
| Benchmark | Claude Sonnet 4 | Phi 3 Small 8k Instruct |
|---|---|---|
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Claude Sonnet 4 leads
Claude Sonnet 4: 22.9 (#187), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | Claude Sonnet 4 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1100 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| EnigmaEval | 3.1% | — |
| LiveBench Reasoning | — | 15.9% |
| DTBench | 77.1% | — |
| LiveBench Data Analysis | — | 30.3% |
| LMCA | 29% | — |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 141.69 | — |
| ForecastBench | 60.2 | — |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | Claude Sonnet 4 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1375 | 1151 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| Omni-MATH | 60.2% | — |
| LiveBench Math | — | 17.6% |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | Claude Sonnet 4 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1372 | 1067 |
| GPQA Diamond | 79.2% | — |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multimodal Not comparable
Claude Sonnet 4: 26.2 (#121), Phi 3 Small 8k Instruct: —
| Benchmark | Claude Sonnet 4 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Claude Sonnet 4 leads
Claude Sonnet 4: 46.7 (#156), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | Claude Sonnet 4 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1333 | 1058 |
| LMArena Chinese | 1350 | 1061 |
| LMArena French | 1363 | 1135 |
| LMArena German | 1331 | 1080 |
| LMArena Japanese | 1302 | 966 |
| LMArena Korean | 1291 | 894 |
| LMArena Russian | 1355 | 1111 |
| LMArena Spanish | 1357 | 1111 |
Instruction Following Claude Sonnet 4 leads
Claude Sonnet 4: 71.7 (#145), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | Claude Sonnet 4 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1376 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
| IFEval | 84% | — |
Long Context Too close to call
Claude Sonnet 4: 33.7 (#259), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | Claude Sonnet 4 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1398 | 1088 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.1 (#132), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | Claude Sonnet 4 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1351 | 1110 |
| LMArena Creative Writing | 1345 | 1083 |
| LMArena Multi-Turn | 1376 | 1068 |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
| LiveBench Language | — | 12.9% |
Frequently asked questions
Is Claude Sonnet 4 better than Phi 3 Small 8k Instruct?
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 29.3 on the Noometry Index.
Is Claude Sonnet 4 or Phi 3 Small 8k Instruct better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 27.9 in the Noometry coding category.
How many benchmarks do Claude Sonnet 4 and Phi 3 Small 8k Instruct share?
17 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Phi 3 Small 8k Instruct has 32.