Model comparison
Gemini 2.5 Flash-Lite vs Llama 4 Scout
Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 27.4 on the Noometry Index.
Last verified . 30 shared benchmarks.
Google
MetaSummary
- They share 30 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 9 categories and Llama 4 Scout in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 2.5 Flash-Lite leads 57.0 to 37.1.
- The biggest single-benchmark swing is MMLU-Pro: 53.7% for Gemini 2.5 Flash-Lite and 74.2% for Llama 4 Scout.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.10 / $0.40 for Gemini 2.5 Flash-Lite.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 128K.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash-Lite | Llama 4 Scout | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 36.4 | 27.4 |
| Released | 2025-06-17 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 128K |
| Max output | 66K | 4K |
| Input $ / M tokens | $0.10 | $0.10 |
| Output $ / M tokens | $0.40 | $0.30 |
| Results tracked | 33 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 38.0 (#167), Llama 4 Scout: 19.9 (#334)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Scout |
|---|---|---|
| LMArena Coding | 1373 | 1286 |
| SWE-bench Verified (bash only) | — | 9.1% |
| SciCode | — | 17% |
| WeirdML | 35.2% | — |
| BigCodeBench Complete | — | 43.1% |
| ALE-Bench | 325.9 | — |
Agentic & Tool Use Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 27.8 (#89), Llama 4 Scout: 24.4 (#109)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | 28.1% |
Reasoning Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 21.5 (#196), Llama 4 Scout: 9.2 (#339)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Scout |
|---|---|---|
| Kagi LLM Benchmark | 40.5% | 36.9% |
| LMArena Hard Prompts | 1377 | 1266 |
| DTBench | 62.8% | 57.9% |
| LMCA | 18.1% | 12% |
| Epoch Capabilities Index | 133.93 | 129.64 |
| ARC-AGI-2 | — | 0% |
| ARC-AGI-1 | — | 0.5% |
| CritPt | — | 0% |
| ForecastBench | — | 57.5 |
Math Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 35.5 (#144), Llama 4 Scout: 18.4 (#280)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Scout |
|---|---|---|
| Omni-MATH | 48% | 37.3% |
| LMArena Math | 1373 | 1286 |
| OTIS Mock AIME 2024-2025 | — | 7.8% |
| MATH Level 5 | — | 62.3% |
| FrontierMath (Feb 2025 set) | — | 0% |
Knowledge Too close to call
Gemini 2.5 Flash-Lite: 32.1 (#206), Llama 4 Scout: 31.8 (#208)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Scout |
|---|---|---|
| MMLU-Pro | 53.7% | 74.2% |
| Vectara Hallucination Rate | 3.3% | 7.7% |
| GPQA (HELM) | 30.9% | 50.7% |
| LMArena Expert | 1373 | 1236 |
| GPQA Diamond | — | 51.8% |
Multimodal Llama 4 Scout leads
Gemini 2.5 Flash-Lite: 28.6 (#109), Llama 4 Scout: 31.6 (#98)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Scout |
|---|---|---|
| LMArena Vision | 1198 | 1118 |
| VPCT | 30% | — |
| SpatialViz-Bench | — | 34.2% |
Multilingual Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 49.5 (#129), Llama 4 Scout: 41.3 (#207)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1369 | 1253 |
| LMArena Chinese | 1404 | 1256 |
| LMArena French | 1388 | 1283 |
| LMArena German | 1390 | 1274 |
| LMArena Japanese | 1359 | 1209 |
| LMArena Korean | 1358 | 1207 |
| LMArena Russian | 1373 | 1263 |
| LMArena Spanish | 1396 | 1277 |
Instruction Following Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 70.2 (#163), Llama 4 Scout: 66.0 (#212)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Scout |
|---|---|---|
| IFEval | 81% | 81.8% |
| LMArena Instruction Following | 1366 | 1248 |
Long Context Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 33.3 (#257), Llama 4 Scout: 27.5 (#289)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Scout |
|---|---|---|
| Fiction.LiveBench | 47.2% | 36% |
| LMArena Longer Query | 1373 | 1265 |
Writing & Preference Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 57.0 (#130), Llama 4 Scout: 37.1 (#256)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1379 | 1279 |
| LMArena Creative Writing | 1366 | 1249 |
| WildBench | 81.8% | 78% |
| LMArena Multi-Turn | 1367 | 1281 |
| EQ-Bench Creative Writing | — | 783 |
Frequently asked questions
Is Gemini 2.5 Flash-Lite better than Llama 4 Scout?
Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 27.4 on the Noometry Index.
Which is cheaper, Gemini 2.5 Flash-Lite 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; Gemini 2.5 Flash-Lite lists at $0.10 and $0.40.
Is Gemini 2.5 Flash-Lite or Llama 4 Scout better for coding?
Gemini 2.5 Flash-Lite scores higher on coding benchmarks: 38.0 versus 19.9 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash-Lite does, with 1.05M tokens against 128K.
How many benchmarks do Gemini 2.5 Flash-Lite and Llama 4 Scout share?
30 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Llama 4 Scout has 43.