Model comparison
Gemma 2 9B vs Llama 4 Scout
Llama 4 Scout is the stronger model overall, scoring 27.7 to 25.9 on the Noometry Index.
Last verified . 23 shared benchmarks.
Google
MetaSummary
- They share 23 benchmarks with published results for both. Gemma 2 9B scores higher in 3 categories and Llama 4 Scout in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 4 Scout leads 31.9 to 9.7.
- The biggest single-benchmark swing is MATH Level 5: 21% for Gemma 2 9B and 62.3% for Llama 4 Scout.
Side by side
| Gemma 2 9B | Llama 4 Scout | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 25.9 | 27.7 |
| Released | 2024-06-24 | 2025-04-05 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 35 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2 9B leads
Gemma 2 9B: 29.4 (#304), Llama 4 Scout: 20.2 (#339)
| Benchmark | Gemma 2 9B | Llama 4 Scout |
|---|---|---|
| LMArena Coding | 1173 | 1286 |
| BigCodeBench Complete | 40.6% | 43.1% |
| SWE-bench Verified (bash only) | — | 9.1% |
| SciCode | — | 17% |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
Agentic & Tool Use Not comparable
Gemma 2 9B: —, Llama 4 Scout: 24.6 (#119)
| Benchmark | Gemma 2 9B | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.1% |
Reasoning Gemma 2 9B leads
Gemma 2 9B: 15.9 (#309), Llama 4 Scout: 9.1 (#345)
| Benchmark | Gemma 2 9B | Llama 4 Scout |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1266 |
| Epoch Capabilities Index | 119.83 | 129.64 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 36.9% |
| ARC-AGI-1 | — | 0.5% |
| CritPt | — | 0% |
| LiveBench Reasoning | 15.2% | — |
| DTBench | — | 57.9% |
| LiveBench Data Analysis | 36.4% | — |
| LMCA | — | 12% |
| ForecastBench | — | 57.5 |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math Llama 4 Scout leads
Gemma 2 9B: 9.9 (#318), Llama 4 Scout: 19.6 (#286)
| Benchmark | Gemma 2 9B | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 7.8% |
| LMArena Math | 1183 | 1287 |
| MATH Level 5 | 21% | 62.3% |
| Omni-MATH | — | 37.3% |
| LiveBench Math | 19.8% | — |
| FrontierMath (Feb 2025 set) | — | 0% |
| GSM8K | 84.9% | — |
Knowledge Llama 4 Scout leads
Gemma 2 9B: 9.7 (#305), Llama 4 Scout: 31.9 (#217)
| Benchmark | Gemma 2 9B | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 27.5% | 51.8% |
| LMArena Expert | 1147 | 1235 |
| MMLU-Pro | — | 74.2% |
| Vectara Hallucination Rate | — | 7.7% |
| GPQA (HELM) | — | 50.7% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multimodal Not comparable
Gemma 2 9B: —, Llama 4 Scout: 32.2 (#102)
| Benchmark | Gemma 2 9B | Llama 4 Scout |
|---|---|---|
| LMArena Vision | — | 1118 |
| SpatialViz-Bench | — | 34.2% |
Multilingual Llama 4 Scout leads
Gemma 2 9B: 36.6 (#238), Llama 4 Scout: 41.0 (#212)
| Benchmark | Gemma 2 9B | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1188 | 1252 |
| LMArena Chinese | 1185 | 1255 |
| LMArena French | 1190 | 1282 |
| LMArena German | 1186 | 1272 |
| LMArena Japanese | 1144 | 1206 |
| LMArena Korean | 1137 | 1207 |
| LMArena Russian | 1200 | 1263 |
| LMArena Spanish | 1200 | 1278 |
Instruction Following Llama 4 Scout leads
Gemma 2 9B: 57.6 (#269), Llama 4 Scout: 65.8 (#217)
| Benchmark | Gemma 2 9B | Llama 4 Scout |
|---|---|---|
| LMArena Instruction Following | 1178 | 1248 |
| LiveBench Instruction Following | 52.6% | — |
| IFEval | — | 81.8% |
Long Context Gemma 2 9B leads
Gemma 2 9B: 36.3 (#233), Llama 4 Scout: 27.5 (#294)
| Benchmark | Gemma 2 9B | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1197 | 1265 |
| Fiction.LiveBench | — | 36% |
Writing & Preference Llama 4 Scout leads
Gemma 2 9B: 32.1 (#281), Llama 4 Scout: 37.0 (#261)
| Benchmark | Gemma 2 9B | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1207 | 1279 |
| LMArena Creative Writing | 1206 | 1249 |
| EQ-Bench Creative Writing | 841 | 783 |
| LMArena Multi-Turn | 1193 | 1280 |
| WildBench | — | 78% |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Llama 4 Scout?
Llama 4 Scout is the stronger model overall, scoring 27.7 to 25.9 on the Noometry Index.
Is Gemma 2 9B or Llama 4 Scout better for coding?
Gemma 2 9B scores higher on coding benchmarks: 29.4 versus 20.2 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Llama 4 Scout share?
23 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Llama 4 Scout has 43.