Model comparison
Gemini 1.5 Flash 8B vs Llama-3.3-70B-Instruct
Gemini 1.5 Flash 8B and Llama-3.3-70B-Instruct score almost the same on the Noometry Index (29.7 vs 30.3), so choose on price, context window or the category you care about most.
Last verified . 20 shared benchmarks.
Google
MetaSummary
- They share 20 benchmarks with published results for both. Gemini 1.5 Flash 8B scores higher in 3 categories and Llama-3.3-70B-Instruct in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama-3.3-70B-Instruct leads 30.5 to 16.0.
- The biggest single-benchmark swing is GPQA Diamond: 33% for Gemini 1.5 Flash 8B and 47.4% for Llama-3.3-70B-Instruct.
- Llama-3.3-70B-Instruct has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Flash 8B | Llama-3.3-70B-Instruct | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 29.7 | 30.3 |
| Released | 2024-10-03 | 2024-12-06 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.32 |
| Results tracked | 21 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.5 Flash 8B leads
Gemini 1.5 Flash 8B: 34.9 (#221), Llama-3.3-70B-Instruct: 30.6 (#284)
| Benchmark | Gemini 1.5 Flash 8B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Coding | 1218 | 1268 |
| SciCode | — | 26% |
| WeirdML | — | 14.4% |
| BigCodeBench Instruct | — | 46.9% |
| LiveBench Coding | — | 36.6% |
| BigCodeBench Complete | — | 57.5% |
Agentic & Tool Use Not comparable
Gemini 1.5 Flash 8B: —, Llama-3.3-70B-Instruct: 25.6 (#100)
| Benchmark | Gemini 1.5 Flash 8B | Llama-3.3-70B-Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 31.9% |
| BALROG | — | 23% |
Reasoning Gemini 1.5 Flash 8B leads
Gemini 1.5 Flash 8B: 19.2 (#242), Llama-3.3-70B-Instruct: 13.7 (#325)
| Benchmark | Gemini 1.5 Flash 8B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Hard Prompts | 1210 | 1257 |
| DTBench | 50% | 59.5% |
| SimpleBench | — | 19.9% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 50.8% |
| LiveBench Data Analysis | — | 49.5% |
| LMCA | — | 17.5% |
| Epoch Capabilities Index | — | 127.32 |
| ForecastBench | — | 58.6 |
| LiveBench | — | 50.2% |
Math Too close to call
Gemini 1.5 Flash 8B: 13.3 (#296), Llama-3.3-70B-Instruct: 14.3 (#292)
| Benchmark | Gemini 1.5 Flash 8B | Llama-3.3-70B-Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.6% | 5.1% |
| LMArena Math | 1207 | 1268 |
| LiveBench Math | — | 42.2% |
| MATH Level 5 | — | 41.6% |
Knowledge Llama-3.3-70B-Instruct leads
Gemini 1.5 Flash 8B: 16.0 (#285), Llama-3.3-70B-Instruct: 30.5 (#220)
| Benchmark | Gemini 1.5 Flash 8B | Llama-3.3-70B-Instruct |
|---|---|---|
| GPQA Diamond | 33% | 47.4% |
| LMArena Expert | 1185 | 1225 |
| Confabulations | — | 22.8% |
| Vectara Hallucination Rate | — | 4.1% |
| MMLU | — | 86.3% |
Multimodal Not comparable
Gemini 1.5 Flash 8B: 27.6 (#110), Llama-3.3-70B-Instruct: —
| Benchmark | Gemini 1.5 Flash 8B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Vision | 1044 | — |
Multilingual Llama-3.3-70B-Instruct leads
Gemini 1.5 Flash 8B: 38.6 (#224), Llama-3.3-70B-Instruct: 40.1 (#215)
| Benchmark | Gemini 1.5 Flash 8B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Non-English | 1215 | 1236 |
| LMArena Chinese | 1231 | 1217 |
| LMArena French | 1233 | 1280 |
| LMArena German | 1206 | 1251 |
| LMArena Japanese | 1150 | 1149 |
| LMArena Korean | 1140 | 1142 |
| LMArena Russian | 1236 | 1252 |
| LMArena Spanish | 1212 | 1269 |
Instruction Following Llama-3.3-70B-Instruct leads
Gemini 1.5 Flash 8B: 63.1 (#231), Llama-3.3-70B-Instruct: 71.3 (#152)
| Benchmark | Gemini 1.5 Flash 8B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Instruction Following | 1199 | 1242 |
| LiveBench Instruction Following | — | 82.7% |
Long Context Gemini 1.5 Flash 8B leads
Gemini 1.5 Flash 8B: 36.9 (#220), Llama-3.3-70B-Instruct: 26.4 (#290)
| Benchmark | Gemini 1.5 Flash 8B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Longer Query | 1219 | 1256 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference Llama-3.3-70B-Instruct leads
Gemini 1.5 Flash 8B: 43.0 (#227), Llama-3.3-70B-Instruct: 47.8 (#203)
| Benchmark | Gemini 1.5 Flash 8B | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Text | 1226 | 1274 |
| LMArena Creative Writing | 1218 | 1250 |
| LMArena Multi-Turn | 1185 | 1279 |
| LiveBench Language | — | 39.2% |
Frequently asked questions
Is Gemini 1.5 Flash 8B better than Llama-3.3-70B-Instruct?
Gemini 1.5 Flash 8B and Llama-3.3-70B-Instruct score almost the same on the Noometry Index (29.7 vs 30.3), so choose on price, context window or the category you care about most.
Is Gemini 1.5 Flash 8B or Llama-3.3-70B-Instruct better for coding?
Gemini 1.5 Flash 8B scores higher on coding benchmarks: 34.9 versus 30.6 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Flash 8B and Llama-3.3-70B-Instruct share?
20 benchmarks have published results for both models. Gemini 1.5 Flash 8B has 21 scored results on Noometry and Llama-3.3-70B-Instruct has 43.