Model comparison
Gemma 2 27B vs Llama 4 Scout
Gemma 2 27B is the stronger model overall, scoring 29.4 to 27.7 on the Noometry Index. Llama 4 Scout costs 4.3× less per token, which makes it the better buy when Gemma 2 27B's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
Google
MetaSummary
- They share 24 benchmarks with published results for both. Gemma 2 27B scores higher in 4 categories and Llama 4 Scout in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Gemma 2 27B leads 34.1 to 20.2.
- The biggest single-benchmark swing is MATH Level 5: 27.9% for Gemma 2 27B and 62.3% for Llama 4 Scout.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
- Llama 4 Scout accepts more context: 128K tokens versus 8K.
Side by side
| Gemma 2 27B | Llama 4 Scout | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 29.4 | 27.7 |
| Released | 2024-06-24 | 2025-04-05 |
| Weights | Open | Open |
| Context window | 8K | 128K |
| Max output | 2K | 4K |
| Input $ / M tokens | $0.65 | $0.10 |
| Output $ / M tokens | $0.65 | $0.30 |
| Results tracked | 34 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2 27B leads
Gemma 2 27B: 34.1 (#246), Llama 4 Scout: 20.2 (#339)
| Benchmark | Gemma 2 27B | Llama 4 Scout |
|---|---|---|
| LMArena Coding | 1211 | 1286 |
| BigCodeBench Complete | 52.5% | 43.1% |
| SWE-bench Verified (bash only) | — | 9.1% |
| SciCode | — | 17% |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
Agentic & Tool Use Not comparable
Gemma 2 27B: —, Llama 4 Scout: 24.6 (#119)
| Benchmark | Gemma 2 27B | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.1% |
Reasoning Gemma 2 27B leads
Gemma 2 27B: 15.3 (#315), Llama 4 Scout: 9.1 (#345)
| Benchmark | Gemma 2 27B | Llama 4 Scout |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1266 |
| DTBench | 48% | 57.9% |
| LMCA | 7.1% | 12% |
| Epoch Capabilities Index | 122.08 | 129.64 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 36.9% |
| ARC-AGI-1 | — | 0.5% |
| CritPt | — | 0% |
| LiveBench Reasoning | 28.1% | — |
| LiveBench Data Analysis | 47.9% | — |
| ForecastBench | — | 57.5 |
| LiveBench | 38.2% | — |
Math Llama 4 Scout leads
Gemma 2 27B: 10.7 (#311), Llama 4 Scout: 19.6 (#286)
| Benchmark | Gemma 2 27B | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.4% | 7.8% |
| LMArena Math | 1212 | 1287 |
| MATH Level 5 | 27.9% | 62.3% |
| Omni-MATH | — | 37.3% |
| LiveBench Math | 26.5% | — |
| FrontierMath (Feb 2025 set) | — | 0% |
Knowledge Llama 4 Scout leads
Gemma 2 27B: 19.0 (#280), Llama 4 Scout: 31.9 (#217)
| Benchmark | Gemma 2 27B | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 36.5% | 51.8% |
| LMArena Expert | 1172 | 1235 |
| MMLU-Pro | — | 74.2% |
| Confabulations | 27.1% | — |
| Vectara Hallucination Rate | — | 7.7% |
| GPQA (HELM) | — | 50.7% |
| MMLU | 75.7% | — |
Multimodal Not comparable
Gemma 2 27B: —, Llama 4 Scout: 32.2 (#102)
| Benchmark | Gemma 2 27B | Llama 4 Scout |
|---|---|---|
| LMArena Vision | — | 1118 |
| SpatialViz-Bench | — | 34.2% |
Multilingual Llama 4 Scout leads
Gemma 2 27B: 38.6 (#226), Llama 4 Scout: 41.0 (#212)
| Benchmark | Gemma 2 27B | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1217 | 1252 |
| LMArena Chinese | 1221 | 1255 |
| LMArena French | 1247 | 1282 |
| LMArena German | 1209 | 1272 |
| LMArena Japanese | 1175 | 1206 |
| LMArena Korean | 1174 | 1207 |
| LMArena Russian | 1234 | 1263 |
| LMArena Spanish | 1228 | 1278 |
Instruction Following Llama 4 Scout leads
Gemma 2 27B: 60.5 (#249), Llama 4 Scout: 65.8 (#217)
| Benchmark | Gemma 2 27B | Llama 4 Scout |
|---|---|---|
| LMArena Instruction Following | 1206 | 1248 |
| LiveBench Instruction Following | 58.1% | — |
| IFEval | — | 81.8% |
Long Context Gemma 2 27B leads
Gemma 2 27B: 37.3 (#218), Llama 4 Scout: 27.5 (#294)
| Benchmark | Gemma 2 27B | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1231 | 1265 |
| Fiction.LiveBench | — | 36% |
Writing & Preference Gemma 2 27B leads
Gemma 2 27B: 44.2 (#225), Llama 4 Scout: 37.0 (#261)
| Benchmark | Gemma 2 27B | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1231 | 1279 |
| LMArena Creative Writing | 1241 | 1249 |
| LMArena Multi-Turn | 1224 | 1280 |
| EQ-Bench Creative Writing | — | 783 |
| WildBench | — | 78% |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than Llama 4 Scout?
Gemma 2 27B is the stronger model overall, scoring 29.4 to 27.7 on the Noometry Index. Llama 4 Scout costs 4.3× less per token, which makes it the better buy when Gemma 2 27B's lead doesn't matter for your workload.
Which is cheaper, Gemma 2 27B or Llama 4 Scout?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.
Is Gemma 2 27B or Llama 4 Scout better for coding?
Gemma 2 27B scores higher on coding benchmarks: 34.1 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Llama 4 Scout does, with 128K tokens against 8K.
How many benchmarks do Gemma 2 27B and Llama 4 Scout share?
24 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Llama 4 Scout has 43.