Model comparison
Gemini 2.5 Flash-Lite vs Llama 4 Maverick
Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 30.6 on the Noometry Index.
Last verified . 32 shared benchmarks.
Google
MetaSummary
- They share 32 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 6 categories and Llama 4 Maverick in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 2.5 Flash-Lite leads 57.0 to 39.0.
- The biggest single-benchmark swing is GPQA (HELM): 30.9% for Gemini 2.5 Flash-Lite and 65% for Llama 4 Maverick.
- Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.19 / $0.65 for Llama 4 Maverick.
- Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 128K.
- Llama 4 Maverick has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash-Lite | Llama 4 Maverick | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 36.4 | 30.6 |
| Released | 2025-06-17 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 128K |
| Max output | 66K | 4K |
| Input $ / M tokens | $0.10 | $0.19 |
| Output $ / M tokens | $0.40 | $0.65 |
| Results tracked | 33 | 54 |
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 Maverick: 26.3 (#318)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| WeirdML | 35.2% | 24.5% |
| LMArena Coding | 1373 | 1302 |
| ALE-Bench | 325.9 | 172.97 |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| SciCode | — | 33.1% |
| BigCodeBench Instruct | — | 49.7% |
| BigCodeBench Complete | — | 61.4% |
Agentic & Tool Use Too close to call
Gemini 2.5 Flash-Lite: 27.8 (#89), Llama 4 Maverick: 27.9 (#86)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | 36.9% | 37.3% |
Reasoning Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 21.5 (#196), Llama 4 Maverick: 10.1 (#337)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| Kagi LLM Benchmark | 40.5% | 55.9% |
| LMArena Hard Prompts | 1377 | 1281 |
| DTBench | 62.8% | 61.9% |
| LMCA | 18.1% | 15.9% |
| Epoch Capabilities Index | 133.93 | 132.2 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 27.7% |
| NYT Connections (extended) | — | 8% |
| ARC-AGI-1 | — | 4.4% |
| CritPt | — | 0% |
| EnigmaEval | — | 0.6% |
| ForecastBench | — | 57.5 |
Math Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 35.5 (#144), Llama 4 Maverick: 24.6 (#256)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| Omni-MATH | 48% | 42.2% |
| LMArena Math | 1373 | 1299 |
| OTIS Mock AIME 2024-2025 | — | 20.6% |
| MATH Level 5 | — | 73% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge Llama 4 Maverick leads
Gemini 2.5 Flash-Lite: 32.1 (#206), Llama 4 Maverick: 33.3 (#196)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| MMLU-Pro | 53.7% | 81% |
| Vectara Hallucination Rate | 3.3% | 8.2% |
| GPQA (HELM) | 30.9% | 65% |
| LMArena Expert | 1373 | 1259 |
| GPQA Diamond | — | 67% |
| Humanity's Last Exam | — | 5.7% |
| Confabulations | — | 22.6% |
Multimodal Llama 4 Maverick leads
Gemini 2.5 Flash-Lite: 28.6 (#109), Llama 4 Maverick: 30.9 (#100)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | 1198 | 1141 |
| GeoBench | — | 52% |
| VPCT | 30% | — |
| SpatialViz-Bench | — | 31.8% |
Multilingual Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 49.5 (#129), Llama 4 Maverick: 42.4 (#190)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1369 | 1269 |
| LMArena Chinese | 1404 | 1277 |
| LMArena French | 1388 | 1258 |
| LMArena German | 1390 | 1291 |
| LMArena Japanese | 1359 | 1207 |
| LMArena Korean | 1358 | 1203 |
| LMArena Russian | 1373 | 1286 |
| LMArena Spanish | 1396 | 1293 |
Instruction Following Llama 4 Maverick leads
Gemini 2.5 Flash-Lite: 70.2 (#163), Llama 4 Maverick: 71.9 (#140)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| IFEval | 81% | 90.8% |
| LMArena Instruction Following | 1366 | 1267 |
Long Context Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 33.3 (#257), Llama 4 Maverick: 31.4 (#274)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| Fiction.LiveBench | 47.2% | 46.2% |
| LMArena Longer Query | 1373 | 1280 |
Writing & Preference Gemini 2.5 Flash-Lite leads
Gemini 2.5 Flash-Lite: 57.0 (#130), Llama 4 Maverick: 39.0 (#247)
| Benchmark | Gemini 2.5 Flash-Lite | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1379 | 1287 |
| LMArena Creative Writing | 1366 | 1266 |
| WildBench | 81.8% | 80% |
| LMArena Multi-Turn | 1367 | 1289 |
| Short-Story Creative Writing | — | 62% |
| EQ-Bench Creative Writing | — | 860 |
Frequently asked questions
Is Gemini 2.5 Flash-Lite better than Llama 4 Maverick?
Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 30.6 on the Noometry Index.
Which is cheaper, Gemini 2.5 Flash-Lite or Llama 4 Maverick?
Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Llama 4 Maverick lists at $0.19 and $0.65.
Is Gemini 2.5 Flash-Lite or Llama 4 Maverick better for coding?
Gemini 2.5 Flash-Lite scores higher on coding benchmarks: 38.0 versus 26.3 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 Maverick share?
32 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Llama 4 Maverick has 54.