Model comparison
Gemini 1.0 Pro vs Llama 4 Maverick
Llama 4 Maverick is the stronger model overall, scoring 30.6 to 27.1 on the Noometry Index.
Last verified . 21 shared benchmarks.
Google
MetaSummary
- They share 21 benchmarks with published results for both. Gemini 1.0 Pro scores higher in 3 categories and Llama 4 Maverick in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 4 Maverick leads 33.3 to 15.5.
- The biggest single-benchmark swing is MATH Level 5: 11.2% for Gemini 1.0 Pro and 73% for Llama 4 Maverick.
- Llama 4 Maverick has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.0 Pro | Llama 4 Maverick | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 27.1 | 30.6 |
| Released | 2023-12-13 | 2025-04-05 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.19 |
| Output $ / M tokens | — | $0.65 |
| Results tracked | 24 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.0 Pro leads
Gemini 1.0 Pro: 31.6 (#270), Llama 4 Maverick: 26.3 (#318)
| Benchmark | Gemini 1.0 Pro | Llama 4 Maverick |
|---|---|---|
| LMArena Coding | 1108 | 1302 |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| SciCode | — | 33.1% |
| WeirdML | — | 24.5% |
| BigCodeBench Instruct | — | 49.7% |
| BigCodeBench Complete | — | 61.4% |
| ALE-Bench | — | 172.97 |
| HumanEval+ | 55.5% | — |
| MBPP+ | 61.4% | — |
Agentic & Tool Use Not comparable
Gemini 1.0 Pro: —, Llama 4 Maverick: 27.9 (#86)
| Benchmark | Gemini 1.0 Pro | Llama 4 Maverick |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.3% |
Reasoning Gemini 1.0 Pro leads
Gemini 1.0 Pro: 16.4 (#292), Llama 4 Maverick: 10.1 (#337)
| Benchmark | Gemini 1.0 Pro | Llama 4 Maverick |
|---|---|---|
| LMArena Hard Prompts | 1109 | 1281 |
| DTBench | 45.9% | 61.9% |
| Epoch Capabilities Index | 116.97 | 132.2 |
| 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% |
| LMCA | — | 15.9% |
| ForecastBench | — | 57.5 |
Math Llama 4 Maverick leads
Gemini 1.0 Pro: 8.7 (#315), Llama 4 Maverick: 24.6 (#256)
| Benchmark | Gemini 1.0 Pro | Llama 4 Maverick |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 20.6% |
| LMArena Math | 1132 | 1299 |
| MATH Level 5 | 11.2% | 73% |
| Omni-MATH | — | 42.2% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge Llama 4 Maverick leads
Gemini 1.0 Pro: 15.5 (#286), Llama 4 Maverick: 33.3 (#196)
| Benchmark | Gemini 1.0 Pro | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | 34% | 67% |
| LMArena Expert | 1059 | 1259 |
| Humanity's Last Exam | — | 5.7% |
| MMLU-Pro | — | 81% |
| Confabulations | — | 22.6% |
| Vectara Hallucination Rate | — | 8.2% |
| GPQA (HELM) | — | 65% |
| MMLU | 70% | — |
Multimodal Not comparable
Gemini 1.0 Pro: —, Llama 4 Maverick: 30.9 (#100)
| Benchmark | Gemini 1.0 Pro | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | — | 1141 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |
Multilingual Llama 4 Maverick leads
Gemini 1.0 Pro: 33.5 (#247), Llama 4 Maverick: 42.4 (#190)
| Benchmark | Gemini 1.0 Pro | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1138 | 1269 |
| LMArena Chinese | 1124 | 1277 |
| LMArena French | 1144 | 1258 |
| LMArena German | 1125 | 1291 |
| LMArena Japanese | 1023 | 1207 |
| LMArena Russian | 1186 | 1286 |
| LMArena Spanish | 1118 | 1293 |
| LMArena Korean | — | 1203 |
Instruction Following Llama 4 Maverick leads
Gemini 1.0 Pro: 57.9 (#262), Llama 4 Maverick: 71.9 (#140)
| Benchmark | Gemini 1.0 Pro | Llama 4 Maverick |
|---|---|---|
| LMArena Instruction Following | 1114 | 1267 |
| IFEval | — | 90.8% |
Long Context Gemini 1.0 Pro leads
Gemini 1.0 Pro: 34.3 (#244), Llama 4 Maverick: 31.4 (#274)
| Benchmark | Gemini 1.0 Pro | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1132 | 1280 |
| Fiction.LiveBench | — | 46.2% |
Writing & Preference Llama 4 Maverick leads
Gemini 1.0 Pro: 36.2 (#259), Llama 4 Maverick: 39.0 (#247)
| Benchmark | Gemini 1.0 Pro | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1149 | 1287 |
| LMArena Creative Writing | 1130 | 1266 |
| LMArena Multi-Turn | 1139 | 1289 |
| Short-Story Creative Writing | — | 62% |
| EQ-Bench Creative Writing | — | 860 |
| WildBench | — | 80% |
Frequently asked questions
Is Gemini 1.0 Pro better than Llama 4 Maverick?
Llama 4 Maverick is the stronger model overall, scoring 30.6 to 27.1 on the Noometry Index.
Is Gemini 1.0 Pro or Llama 4 Maverick better for coding?
Gemini 1.0 Pro scores higher on coding benchmarks: 31.6 versus 26.3 in the Noometry coding category.
How many benchmarks do Gemini 1.0 Pro and Llama 4 Maverick share?
21 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and Llama 4 Maverick has 54.