Model comparison
Gemini 1.5 Flash (May 2024) vs Llama 3-70B
Gemini 1.5 Flash (May 2024) is the stronger model overall, scoring 33.2 to 28.8 on the Noometry Index.
Last verified . 28 shared benchmarks.
Google
MetaSummary
- They share 28 benchmarks with published results for both. Gemini 1.5 Flash (May 2024) scores higher in 8 categories and Llama 3-70B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemini 1.5 Flash (May 2024) leads 42.9 to 33.6.
- The biggest single-benchmark swing is MATH Level 5: 61.9% for Gemini 1.5 Flash (May 2024) and 22.6% for Llama 3-70B.
- Llama 3-70B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Flash (May 2024) | Llama 3-70B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 33.2 | 28.8 |
| Released | 2024-05-14 | 2024-04-18 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 42 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Gemini 1.5 Flash (May 2024): 34.4 (#236), Llama 3-70B: 35.8 (#218)
| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3-70B |
|---|---|---|
| BigCodeBench Instruct | 43.5% | 43.6% |
| LMArena Coding | 1261 | 1206 |
| BigCodeBench Complete | 55.1% | 54.5% |
| HumanEval+ | 75.6% | 72% |
| MBPP+ | 67.5% | 69% |
| WeirdML | 24.9% | — |
Agentic & Tool Use Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 26.6 (#102), Llama 3-70B: 21.1 (#139)
Reasoning Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 21.7 (#215), Llama 3-70B: 18.0 (#288)
| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1195 |
| DTBench | 53.8% | 54.2% |
| Epoch Capabilities Index | 129.36 | 122.93 |
| ForecastBench | 53.9 | 57.1 |
| Kagi LLM Benchmark | — | 35.1% |
| PIQA | 87.5% | — |
| WinoGrande | — | 83.5% |
Math Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 22.1 (#281), Llama 3-70B: 12.8 (#305)
| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.3% | 4.3% |
| LMArena Math | 1269 | 1218 |
| MATH Level 5 | 61.9% | 22.6% |
| Omni-MATH | 30.4% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
| GSM8K | 82.4% | — |
Knowledge Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 26.2 (#260), Llama 3-70B: 20.8 (#277)
| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3-70B |
|---|---|---|
| GPQA Diamond | 47.3% | 40.6% |
| LMArena Expert | 1233 | 1149 |
| MMLU | 77.9% | 79.3% |
| MMLU-Pro | 67.8% | — |
| GPQA (HELM) | 43.7% | — |
| BoolQ | 85.8% | — |
Multimodal Not comparable
Gemini 1.5 Flash (May 2024): 36.0 (#81), Llama 3-70B: —
| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3-70B |
|---|---|---|
| LMArena Vision | 1141 | — |
| Video-MME | 70.3% | — |
| GeoBench | 76% | — |
Multilingual Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 42.9 (#189), Llama 3-70B: 33.6 (#251)
| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1278 | 1142 |
| LMArena Chinese | 1295 | 1114 |
| LMArena French | 1258 | 1232 |
| LMArena German | 1262 | 1169 |
| LMArena Japanese | 1252 | 1017 |
| LMArena Korean | 1221 | 1017 |
| LMArena Russian | 1288 | 1159 |
| LMArena Spanish | 1243 | 1241 |
Instruction Following Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 66.8 (#205), Llama 3-70B: 62.5 (#238)
| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1258 | 1194 |
| IFEval | 83.1% | — |
Long Context Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 39.0 (#187), Llama 3-70B: 35.6 (#240)
| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1284 | 1174 |
Writing & Preference Gemini 1.5 Flash (May 2024) leads
Gemini 1.5 Flash (May 2024): 48.7 (#196), Llama 3-70B: 42.8 (#231)
| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3-70B |
|---|---|---|
| LMArena Text | 1287 | 1221 |
| LMArena Creative Writing | 1285 | 1210 |
| LMArena Multi-Turn | 1253 | 1223 |
| WildBench | 79.2% | — |
Frequently asked questions
Is Gemini 1.5 Flash (May 2024) better than Llama 3-70B?
Gemini 1.5 Flash (May 2024) is the stronger model overall, scoring 33.2 to 28.8 on the Noometry Index.
Is Gemini 1.5 Flash (May 2024) or Llama 3-70B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.8 versus 34.4 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Flash (May 2024) and Llama 3-70B share?
28 benchmarks have published results for both models. Gemini 1.5 Flash (May 2024) has 42 scored results on Noometry and Llama 3-70B has 31.