Model comparison
Gemini 2.0 Flash-Lite vs Llama 4 Maverick
Gemini 2.0 Flash-Lite is the stronger model overall, scoring 37.3 to 30.6 on the Noometry Index.
Last verified . 25 shared benchmarks.
Google
MetaSummary
- They share 25 benchmarks with published results for both. Gemini 2.0 Flash-Lite scores higher in 7 categories and Llama 4 Maverick in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 2.0 Flash-Lite leads 51.9 to 39.0.
- The biggest single-benchmark swing is GPQA (HELM): 50% for Gemini 2.0 Flash-Lite and 65% for Llama 4 Maverick.
- Llama 4 Maverick has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash-Lite | Llama 4 Maverick | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 37.3 | 30.6 |
| Released | 2025-02-05 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.19 |
| Output $ / M tokens | — | $0.65 |
| Results tracked | 32 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 37.4 (#181), Llama 4 Maverick: 26.3 (#318)
| Benchmark | Gemini 2.0 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| LMArena Coding | 1322 | 1302 |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| SciCode | — | 33.1% |
| WeirdML | — | 24.5% |
| BigCodeBench Instruct | — | 49.7% |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | — | 61.4% |
| ALE-Bench | — | 172.97 |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash-Lite: —, Llama 4 Maverick: 27.9 (#86)
| Benchmark | Gemini 2.0 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.3% |
Reasoning Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 21.2 (#203), Llama 4 Maverick: 10.1 (#337)
| Benchmark | Gemini 2.0 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| LMArena Hard Prompts | 1324 | 1281 |
| DTBench | 52.5% | 61.9% |
| ForecastBench | 57.1 | 57.5 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 27.7% |
| Kagi LLM Benchmark | — | 55.9% |
| NYT Connections (extended) | — | 8% |
| ARC-AGI-1 | — | 4.4% |
| CritPt | — | 0% |
| EnigmaEval | — | 0.6% |
| LiveBench Reasoning | 50.1% | — |
| LiveBench Data Analysis | 65.5% | — |
| LMCA | — | 15.9% |
| Epoch Capabilities Index | — | 132.2 |
| LiveBench | 54.3% | — |
Math Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 31.8 (#192), Llama 4 Maverick: 24.6 (#256)
| Benchmark | Gemini 2.0 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| Omni-MATH | 37.4% | 42.2% |
| LMArena Math | 1309 | 1299 |
| OTIS Mock AIME 2024-2025 | — | 20.6% |
| LiveBench Math | 58.1% | — |
| MATH Level 5 | — | 73% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 34.6 (#185), Llama 4 Maverick: 33.3 (#196)
| Benchmark | Gemini 2.0 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| MMLU-Pro | 72% | 81% |
| GPQA (HELM) | 50% | 65% |
| LMArena Expert | 1305 | 1259 |
| GPQA Diamond | — | 67% |
| Humanity's Last Exam | — | 5.7% |
| Confabulations | — | 22.6% |
| Vectara Hallucination Rate | — | 8.2% |
Multimodal Too close to call
Gemini 2.0 Flash-Lite: 30.6 (#103), Llama 4 Maverick: 30.9 (#100)
| Benchmark | Gemini 2.0 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | 1100 | 1141 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |
Multilingual Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 46.2 (#156), Llama 4 Maverick: 42.4 (#190)
| Benchmark | Gemini 2.0 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1323 | 1269 |
| LMArena Chinese | 1339 | 1277 |
| LMArena French | 1346 | 1258 |
| LMArena German | 1306 | 1291 |
| LMArena Japanese | 1302 | 1207 |
| LMArena Korean | 1325 | 1203 |
| LMArena Russian | 1328 | 1286 |
| LMArena Spanish | 1313 | 1293 |
Instruction Following Llama 4 Maverick leads
Gemini 2.0 Flash-Lite: 70.6 (#158), Llama 4 Maverick: 71.9 (#140)
| Benchmark | Gemini 2.0 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| IFEval | 82.4% | 90.8% |
| LMArena Instruction Following | 1305 | 1267 |
| LiveBench Instruction Following | 78.3% | — |
Long Context Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 40.1 (#155), Llama 4 Maverick: 31.4 (#274)
| Benchmark | Gemini 2.0 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1321 | 1280 |
| Fiction.LiveBench | — | 46.2% |
Writing & Preference Gemini 2.0 Flash-Lite leads
Gemini 2.0 Flash-Lite: 51.9 (#172), Llama 4 Maverick: 39.0 (#247)
| Benchmark | Gemini 2.0 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1330 | 1287 |
| LMArena Creative Writing | 1319 | 1266 |
| WildBench | 79% | 80% |
| LMArena Multi-Turn | 1307 | 1289 |
| Short-Story Creative Writing | — | 62% |
| EQ-Bench Creative Writing | — | 860 |
| LiveBench Language | 34.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash-Lite better than Llama 4 Maverick?
Gemini 2.0 Flash-Lite is the stronger model overall, scoring 37.3 to 30.6 on the Noometry Index.
Is Gemini 2.0 Flash-Lite or Llama 4 Maverick better for coding?
Gemini 2.0 Flash-Lite scores higher on coding benchmarks: 37.4 versus 26.3 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash-Lite and Llama 4 Maverick share?
25 benchmarks have published results for both models. Gemini 2.0 Flash-Lite has 32 scored results on Noometry and Llama 4 Maverick has 54.