Model comparison
Llama 4 Scout vs Phi 3 Small 8k Instruct
Phi 3 Small 8k Instruct is the stronger model overall, scoring 29.3 to 27.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
MicrosoftSummary
- They share 17 benchmarks with published results for both. Llama 4 Scout scores higher in 4 categories and Phi 3 Small 8k Instruct in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama 4 Scout leads 65.8 to 51.9.
Side by side
| Llama 4 Scout | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 27.7 | 29.3 |
| Released | 2025-04-05 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 43 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi 3 Small 8k Instruct leads
Llama 4 Scout: 20.2 (#339), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | Llama 4 Scout | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1286 | 1101 |
| SWE-bench Verified (bash only) | 9.1% | — |
| SciCode | 17% | — |
| LiveBench Coding | — | 20.3% |
| BigCodeBench Complete | 43.1% | — |
Agentic & Tool Use Not comparable
Llama 4 Scout: 24.6 (#119), Phi 3 Small 8k Instruct: —
| Benchmark | Llama 4 Scout | Phi 3 Small 8k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
Reasoning Phi 3 Small 8k Instruct leads
Llama 4 Scout: 9.1 (#345), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | Llama 4 Scout | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1266 | 1100 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 36.9% | — |
| ARC-AGI-1 | 0.5% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | — | 15.9% |
| DTBench | 57.9% | — |
| LiveBench Data Analysis | — | 30.3% |
| LMCA | 12% | — |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 129.64 | — |
| ForecastBench | 57.5 | — |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |
Math Phi 3 Small 8k Instruct leads
Llama 4 Scout: 19.6 (#286), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | Llama 4 Scout | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1287 | 1151 |
| OTIS Mock AIME 2024-2025 | 7.8% | — |
| Omni-MATH | 37.3% | — |
| LiveBench Math | — | 17.6% |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Llama 4 Scout leads
Llama 4 Scout: 31.9 (#217), Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | Llama 4 Scout | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1235 | 1067 |
| GPQA Diamond | 51.8% | — |
| MMLU-Pro | 74.2% | — |
| Vectara Hallucination Rate | 7.7% | — |
| GPQA (HELM) | 50.7% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multimodal Not comparable
Llama 4 Scout: 32.2 (#102), Phi 3 Small 8k Instruct: —
| Benchmark | Llama 4 Scout | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |
Multilingual Llama 4 Scout leads
Llama 4 Scout: 41.0 (#212), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | Llama 4 Scout | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1252 | 1058 |
| LMArena Chinese | 1255 | 1061 |
| LMArena French | 1282 | 1135 |
| LMArena German | 1272 | 1080 |
| LMArena Japanese | 1206 | 966 |
| LMArena Korean | 1207 | 894 |
| LMArena Russian | 1263 | 1111 |
| LMArena Spanish | 1278 | 1111 |
Instruction Following Llama 4 Scout leads
Llama 4 Scout: 65.8 (#217), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | Llama 4 Scout | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1248 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
| IFEval | 81.8% | — |
Long Context Phi 3 Small 8k Instruct leads
Llama 4 Scout: 27.5 (#294), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | Llama 4 Scout | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1265 | 1088 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Llama 4 Scout leads
Llama 4 Scout: 37.0 (#261), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | Llama 4 Scout | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1279 | 1110 |
| LMArena Creative Writing | 1249 | 1083 |
| LMArena Multi-Turn | 1280 | 1068 |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
| LiveBench Language | — | 12.9% |
Frequently asked questions
Is Llama 4 Scout better than Phi 3 Small 8k Instruct?
Phi 3 Small 8k Instruct is the stronger model overall, scoring 29.3 to 27.7 on the Noometry Index.
Is Llama 4 Scout or Phi 3 Small 8k Instruct better for coding?
Phi 3 Small 8k Instruct scores higher on coding benchmarks: 27.9 versus 20.2 in the Noometry coding category.
How many benchmarks do Llama 4 Scout and Phi 3 Small 8k Instruct share?
17 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Phi 3 Small 8k Instruct has 32.