Model comparison
Gemini 1.0 Pro vs Llama 3-8B
Gemini 1.0 Pro is the stronger model overall, scoring 27.3 to 25.5 on the Noometry Index.
Last verified . 24 shared benchmarks.
Google
MetaSummary
- They share 24 benchmarks with published results for both. Gemini 1.0 Pro scores higher in 6 categories and Llama 3-8B in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 1.0 Pro leads 15.6 to 7.8.
- The biggest single-benchmark swing is GPQA Diamond: 34% for Gemini 1.0 Pro and 26.1% for Llama 3-8B.
- Llama 3-8B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.0 Pro | Llama 3-8B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 27.3 | 25.5 |
| Released | 2023-12-13 | 2024-04-18 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 34 |
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: 32.2 (#275), Llama 3-8B: 31.0 (#289)
| Benchmark | Gemini 1.0 Pro | Llama 3-8B |
|---|---|---|
| LMArena Coding | 1108 | 1152 |
| HumanEval+ | 55.5% | 56.7% |
| MBPP+ | 61.4% | 54.8% |
| BigCodeBench Instruct | — | 31.9% |
| BigCodeBench Complete | — | 36.9% |
Reasoning Gemini 1.0 Pro leads
Gemini 1.0 Pro: 17.1 (#296), Llama 3-8B: 14.3 (#326)
| Benchmark | Gemini 1.0 Pro | Llama 3-8B |
|---|---|---|
| LMArena Hard Prompts | 1109 | 1133 |
| DTBench | 45.9% | 43.9% |
| Epoch Capabilities Index | 117.04 | 116.45 |
| Chess Puzzles | — | 0% |
| Adversarial NLI | — | 57.3% |
| ForecastBench | — | 58.6 |
| WinoGrande | — | 75.7% |
Math Too close to call
Gemini 1.0 Pro: 9.3 (#321), Llama 3-8B: 8.8 (#323)
| Benchmark | Gemini 1.0 Pro | Llama 3-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 1.9% |
| LMArena Math | 1132 | 1151 |
| MATH Level 5 | 11.2% | 6.1% |
Knowledge Gemini 1.0 Pro leads
Gemini 1.0 Pro: 15.6 (#291), Llama 3-8B: 7.8 (#308)
| Benchmark | Gemini 1.0 Pro | Llama 3-8B |
|---|---|---|
| GPQA Diamond | 34% | 26.1% |
| LMArena Expert | 1059 | 1113 |
| MMLU | 70% | 68.8% |
| ARC (AI2) Challenge | — | 82.8% |
| OpenBookQA | — | 82.6% |
| TriviaQA | — | 67.7% |
Multilingual Gemini 1.0 Pro leads
Gemini 1.0 Pro: 33.4 (#252), Llama 3-8B: 30.8 (#261)
| Benchmark | Gemini 1.0 Pro | Llama 3-8B |
|---|---|---|
| LMArena Non-English | 1138 | 1098 |
| LMArena Chinese | 1124 | 1076 |
| LMArena French | 1145 | 1159 |
| LMArena German | 1125 | 1104 |
| LMArena Japanese | 1023 | 967 |
| LMArena Russian | 1186 | 1109 |
| LMArena Spanish | 1119 | 1173 |
| LMArena Korean | — | 1004 |
Instruction Following Too close to call
Gemini 1.0 Pro: 57.6 (#267), Llama 3-8B: 58.4 (#260)
| Benchmark | Gemini 1.0 Pro | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | 1114 | 1127 |
Long Context Too close to call
Gemini 1.0 Pro: 34.3 (#249), Llama 3-8B: 34.2 (#251)
| Benchmark | Gemini 1.0 Pro | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | 1132 | 1128 |
Writing & Preference Llama 3-8B leads
Gemini 1.0 Pro: 36.0 (#264), Llama 3-8B: 37.5 (#256)
| Benchmark | Gemini 1.0 Pro | Llama 3-8B |
|---|---|---|
| LMArena Text | 1149 | 1166 |
| LMArena Creative Writing | 1131 | 1150 |
| LMArena Multi-Turn | 1139 | 1152 |
Frequently asked questions
Is Gemini 1.0 Pro better than Llama 3-8B?
Gemini 1.0 Pro is the stronger model overall, scoring 27.3 to 25.5 on the Noometry Index.
Is Gemini 1.0 Pro or Llama 3-8B better for coding?
Gemini 1.0 Pro scores higher on coding benchmarks: 32.2 versus 31.0 in the Noometry coding category.
How many benchmarks do Gemini 1.0 Pro and Llama 3-8B share?
24 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and Llama 3-8B has 34.