# Gemini 1.5 Pro (May 2024) vs Llama 3-70B

> Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 31.9 to 28.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-1-5-pro-vs-llama-3-70b
- Last updated: 2026-10-10
- Shared benchmarks: 29

## Summary

- They share 29 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 6 categories and Llama 3-70B in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 1.5 Pro (May 2024) leads 24.4 to 12.0.
- The biggest single-benchmark swing is MATH Level 5: 70.4% for Gemini 1.5 Pro (May 2024) and 22.6% for Llama 3-70B.
- Llama 3-70B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 1.5 Pro (May 2024) | Llama 3-70B |
|---|---|---|
| Provider | Google | Meta |
| Noometry Index | 31.9 | 28.5 |
| Rank | 253 | 317 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Gemini 1.5 Pro (May 2024): 33.8 (#239)
- Llama 3-70B: 35.3 (#215)

| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3-70B |
|---|---|---|
| BigCodeBench Instruct | 43.8% | 43.6% |
| LMArena Coding | 1294 | 1206 |
| BigCodeBench Complete | 57.5% | 54.5% |
| HumanEval+ | 79.3% | 72% |
| MBPP+ | 74.6% | 69% |
| WeirdML | 22.2% | — |
| CadEval | 34% | — |

## Agentic & Tool Use

- Gemini 1.5 Pro (May 2024): 17.8 (#137)
- Llama 3-70B: 20.9 (#132)

| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3-70B |
|---|---|---|
| Cybench | 7.5% | 5% |
| TheAgentCompany | 3.4% | — |
| BALROG | 21% | — |

## Reasoning

- Gemini 1.5 Pro (May 2024): 12.3 (#332)
- Llama 3-70B: 17.4 (#284)

| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3-70B |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1195 |
| DTBench | 59% | 54.2% |
| Epoch Capabilities Index | 131.73 | 122.91 |
| ForecastBench | 58.4 | 57.1 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| Kagi LLM Benchmark | — | 35.1% |
| BIG-Bench Hard | 89.2% | — |
| WinoGrande | — | 83.5% |

## Math

- Gemini 1.5 Pro (May 2024): 24.4 (#260)
- Llama 3-70B: 12.0 (#299)

| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 4.3% |
| LMArena Math | 1315 | 1218 |
| MATH Level 5 | 70.4% | 22.6% |
| Omni-MATH | 36.4% | — |

## Knowledge

- Gemini 1.5 Pro (May 2024): 29.3 (#228)
- Llama 3-70B: 20.8 (#272)

| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3-70B |
|---|---|---|
| GPQA Diamond | 57.2% | 40.6% |
| LMArena Expert | 1279 | 1149 |
| MMLU | 86.9% | 79.3% |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| GPQA (HELM) | 53.4% | — |

## Multimodal

- Gemini 1.5 Pro (May 2024): 36.2 (#72)
- Llama 3-70B: —

| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3-70B |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |

## Multilingual

- Gemini 1.5 Pro (May 2024): 45.5 (#169)
- Llama 3-70B: 33.8 (#246)

| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1312 | 1142 |
| LMArena Chinese | 1331 | 1114 |
| LMArena French | 1301 | 1231 |
| LMArena German | 1286 | 1169 |
| LMArena Japanese | 1292 | 1017 |
| LMArena Korean | 1298 | 1017 |
| LMArena Russian | 1320 | 1159 |
| LMArena Spanish | 1310 | 1241 |

## Instruction Following

- Gemini 1.5 Pro (May 2024): 68.8 (#180)
- Llama 3-70B: 62.8 (#233)

| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1297 | 1194 |
| IFEval | 83.7% | — |

## Long Context

- Gemini 1.5 Pro (May 2024): 39.7 (#164)
- Llama 3-70B: 35.6 (#235)

| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1308 | 1174 |

## Writing & Preference

- Gemini 1.5 Pro (May 2024): 52.5 (#167)
- Llama 3-70B: 43.0 (#225)

| Benchmark | Gemini 1.5 Pro (May 2024) | Llama 3-70B |
|---|---|---|
| LMArena Text | 1319 | 1221 |
| LMArena Creative Writing | 1333 | 1210 |
| LMArena Multi-Turn | 1296 | 1223 |
| WildBench | 81.3% | — |

## FAQ

### Is Gemini 1.5 Pro (May 2024) better than Llama 3-70B?

Gemini 1.5 Pro (May 2024) is the stronger model overall, scoring 31.9 to 28.5 on the Noometry Index.

### Is Gemini 1.5 Pro (May 2024) or Llama 3-70B better for coding?

Llama 3-70B scores higher on coding benchmarks: 35.3 versus 33.8 in the Noometry coding category.

### How many benchmarks do Gemini 1.5 Pro (May 2024) and Llama 3-70B share?

29 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Llama 3-70B has 31.