Model comparison
Gemini 1.5 Pro (May 2024) vs Llama 3.1-8B
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 31.9 to 22.8 on the Noometry Index.
Last verified . 34 shared benchmarks.
Google
MetaSummary
- They share 34 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 7 categories and Llama 3.1-8B in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 1.5 Pro (May 2024) leads 52.5 to 29.9.
- The biggest single-benchmark swing is MATH Level 5: 70.4% for Gemini 1.5 Pro (May 2024) and 22.9% for Llama 3.1-8B.
- Llama 3.1-8B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | Llama 3.1-8B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 31.9 | 22.8 |
| Released | 2024-02-15 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.08 |
| Results tracked | 45 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 33.8 (#239), Llama 3.1-8B: 19.9 (#335)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-8B |
|---|---|---|
| WeirdML | 22.2% | 1.7% |
| BigCodeBench Instruct | 43.8% | 32.8% |
| LMArena Coding | 1294 | 1195 |
| BigCodeBench Complete | 57.5% | 40.5% |
| HumanEval+ | 79.3% | 62.8% |
| MBPP+ | 74.6% | 55.6% |
| SciCode | — | 13.2% |
| CadEval | 34% | — |
Agentic & Tool Use Llama 3.1-8B leads
Gemini 1.5 Pro (May 2024): 17.8 (#137), Llama 3.1-8B: 22.3 (#123)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-8B |
|---|---|---|
| BALROG | 21% | 15.1% |
| Berkeley Function Calling Leaderboard | — | 25.8% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
Reasoning Llama 3.1-8B leads
Gemini 1.5 Pro (May 2024): 12.3 (#332), Llama 3.1-8B: 14.5 (#316)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-8B |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1175 |
| DTBench | 59% | 50.9% |
| Epoch Capabilities Index | 131.73 | 116.48 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| LMCA | — | 5.4% |
| BIG-Bench Hard | 89.2% | — |
| ForecastBench | 58.4 | — |
| PIQA | — | 81.2% |
Math Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 24.4 (#260), Llama 3.1-8B: 9.5 (#311)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 1.7% |
| Omni-MATH | 36.4% | 13.7% |
| LMArena Math | 1315 | 1179 |
| MATH Level 5 | 70.4% | 22.9% |
| GSM8K | — | 82.4% |
Knowledge Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 29.3 (#228), Llama 3.1-8B: 8.0 (#302)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-8B |
|---|---|---|
| GPQA Diamond | 57.2% | 27% |
| MMLU-Pro | 73.7% | 40.6% |
| GPQA (HELM) | 53.4% | 24.7% |
| LMArena Expert | 1279 | 1144 |
| MMLU | 86.9% | 56.1% |
| Humanity's Last Exam | 4.6% | — |
| Confabulations | 13.5% | — |
| BoolQ | — | 82.8% |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.2 (#72), Llama 3.1-8B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-8B |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 45.5 (#169), Llama 3.1-8B: 34.2 (#244)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-8B |
|---|---|---|
| LMArena Non-English | 1312 | 1148 |
| LMArena Chinese | 1331 | 1151 |
| LMArena French | 1301 | 1176 |
| LMArena German | 1286 | 1144 |
| LMArena Japanese | 1292 | 1061 |
| LMArena Korean | 1298 | 1053 |
| LMArena Russian | 1320 | 1158 |
| LMArena Spanish | 1310 | 1169 |
Instruction Following Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 68.8 (#180), Llama 3.1-8B: 59.1 (#253)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-8B |
|---|---|---|
| IFEval | 83.7% | 74.3% |
| LMArena Instruction Following | 1297 | 1159 |
Long Context Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 39.7 (#164), Llama 3.1-8B: 35.8 (#233)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-8B |
|---|---|---|
| LMArena Longer Query | 1308 | 1182 |
Writing & Preference Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 52.5 (#167), Llama 3.1-8B: 29.9 (#285)
| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3.1-8B |
|---|---|---|
| LMArena Text | 1319 | 1187 |
| LMArena Creative Writing | 1333 | 1154 |
| WildBench | 81.3% | 68.7% |
| LMArena Multi-Turn | 1296 | 1172 |
| EQ-Bench Creative Writing | — | 713 |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Llama 3.1-8B?
Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 31.9 to 22.8 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Llama 3.1-8B better for coding?
Gemini 1.5 Pro (May 2024) scores higher on coding benchmarks: 33.8 versus 19.9 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Llama 3.1-8B share?
34 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Llama 3.1-8B has 43.