Model comparison
Gemma 4 31B IT vs Llama 4 Scout
Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 27.4 on the Noometry Index.
Last verified . 25 shared benchmarks.
Google
MetaSummary
- They share 25 benchmarks with published results for both. Gemma 4 31B IT scores higher in 9 categories and Llama 4 Scout in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 4 31B IT leads 60.7 to 37.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 73.3% for Gemma 4 31B IT and 7.8% for Llama 4 Scout.
- Both cost about the same: $0.09 input and $0.34 output per million tokens.
- Gemma 4 31B IT accepts more context: 262K tokens versus 128K.
Side by side
| Gemma 4 31B IT | Llama 4 Scout | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 43.2 | 27.4 |
| Released | 2026-04-02 | 2025-04-05 |
| Weights | Open | Open |
| Context window | 262K | 128K |
| Max output | 33K | 4K |
| Input $ / M tokens | $0.09 | $0.10 |
| Output $ / M tokens | $0.34 | $0.30 |
| Results tracked | 35 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Gemma 4 31B IT: 41.9 (#98), Llama 4 Scout: 19.9 (#334)
| Benchmark | Gemma 4 31B IT | Llama 4 Scout |
|---|---|---|
| SciCode | 43.4% | 17% |
| LMArena Coding | 1459 | 1286 |
| SWE-bench Verified (bash only) | — | 9.1% |
| LMArena WebDev | 1364 | — |
| WeirdML | 52.3% | — |
| BigCodeBench Complete | — | 43.1% |
| ALE-Bench | 925.5 | — |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, Llama 4 Scout: 24.4 (#109)
| Benchmark | Gemma 4 31B IT | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.1% |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 26.4 (#119), Llama 4 Scout: 9.2 (#339)
| Benchmark | Gemma 4 31B IT | Llama 4 Scout |
|---|---|---|
| Kagi LLM Benchmark | 63.5% | 36.9% |
| CritPt | 1.4% | 0% |
| LMArena Hard Prompts | 1448 | 1266 |
| DTBench | 82.7% | 57.9% |
| LMCA | 39.3% | 12% |
| Epoch Capabilities Index | 142.74 | 129.64 |
| ARC-AGI-2 | — | 0% |
| NYT Connections (extended) | 70.6% | — |
| ARC-AGI-1 | — | 0.5% |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| Surface Evolver Bench | 30.6% | — |
| ForecastBench | — | 57.5 |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 41.3 (#72), Llama 4 Scout: 18.4 (#280)
| Benchmark | Gemma 4 31B IT | Llama 4 Scout |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 7.8% |
| LMArena Math | 1464 | 1286 |
| Omni-MATH | — | 37.3% |
| MATH Level 5 | — | 62.3% |
| FrontierMath (Feb 2025 set) | — | 0% |
Knowledge Gemma 4 31B IT leads
Gemma 4 31B IT: 37.9 (#141), Llama 4 Scout: 31.8 (#208)
| Benchmark | Gemma 4 31B IT | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | 75.8% | 51.8% |
| Vectara Hallucination Rate | 7.4% | 7.7% |
| LMArena Expert | 1465 | 1236 |
| SimpleQA Verified | 10.4% | — |
| MMLU-Pro | — | 74.2% |
| GPQA (HELM) | — | 50.7% |
Multimodal Gemma 4 31B IT leads
Gemma 4 31B IT: 41.0 (#32), Llama 4 Scout: 31.6 (#98)
| Benchmark | Gemma 4 31B IT | Llama 4 Scout |
|---|---|---|
| LMArena Vision | 1278 | 1118 |
| LMArena Document | 1425 | — |
| SpatialViz-Bench | — | 34.2% |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 54.0 (#52), Llama 4 Scout: 41.3 (#207)
| Benchmark | Gemma 4 31B IT | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1431 | 1253 |
| LMArena Chinese | 1478 | 1256 |
| LMArena French | 1436 | 1283 |
| LMArena Russian | 1462 | 1263 |
| LMArena Spanish | 1443 | 1277 |
| LMArena German | — | 1274 |
| LMArena Japanese | — | 1209 |
| LMArena Korean | — | 1207 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.6 (#58), Llama 4 Scout: 66.0 (#212)
| Benchmark | Gemma 4 31B IT | Llama 4 Scout |
|---|---|---|
| LMArena Instruction Following | 1433 | 1248 |
| IFEval | — | 81.8% |
Long Context Gemma 4 31B IT leads
Gemma 4 31B IT: 44.2 (#67), Llama 4 Scout: 27.5 (#289)
| Benchmark | Gemma 4 31B IT | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1446 | 1265 |
| Fiction.LiveBench | — | 36% |
Writing & Preference Gemma 4 31B IT leads
Gemma 4 31B IT: 60.7 (#92), Llama 4 Scout: 37.1 (#256)
| Benchmark | Gemma 4 31B IT | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1443 | 1279 |
| LMArena Creative Writing | 1416 | 1249 |
| EQ-Bench Creative Writing | 1368 | 783 |
| LMArena Multi-Turn | 1452 | 1281 |
| WildBench | — | 78% |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Llama 4 Scout?
Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 27.4 on the Noometry Index.
Which is cheaper, Gemma 4 31B IT 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 4 31B IT lists at $0.09 and $0.34.
Is Gemma 4 31B IT or Llama 4 Scout better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 19.9 in the Noometry coding category.
Which has the bigger context window?
Gemma 4 31B IT does, with 262K tokens against 128K.
How many benchmarks do Gemma 4 31B IT and Llama 4 Scout share?
25 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Llama 4 Scout has 43.