# Gemini 1.5 Flash (May 2024) vs Llama 3.1-8B

> Gemini 1.5 Flash (May 2024) is the stronger model overall, scoring 32.9 to 22.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-1-5-flash-vs-llama-3-1-8b
- Last updated: 2026-10-10
- Shared benchmarks: 37

## Summary

- They share 37 benchmarks with published results for both. Gemini 1.5 Flash (May 2024) scores higher in 9 categories and Llama 3.1-8B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 1.5 Flash (May 2024) leads 48.9 to 29.9.
- The biggest single-benchmark swing is MATH Level 5: 61.9% for Gemini 1.5 Flash (May 2024) and 22.9% for Llama 3.1-8B.
- Llama 3.1-8B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 1.5 Flash (May 2024) | Llama 3.1-8B |
|---|---|---|
| Provider | Google | Meta |
| Noometry Index | 32.9 | 22.8 |
| Rank | 240 | 347 |
| Context | — | 128K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.08 |
| Weights | Proprietary | Open |

## Coding

- Gemini 1.5 Flash (May 2024): 33.9 (#233)
- Llama 3.1-8B: 19.9 (#335)

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3.1-8B |
|---|---|---|
| WeirdML | 24.9% | 1.7% |
| BigCodeBench Instruct | 43.5% | 32.8% |
| LMArena Coding | 1262 | 1195 |
| BigCodeBench Complete | 55.1% | 40.5% |
| HumanEval+ | 75.6% | 62.8% |
| MBPP+ | 67.5% | 55.6% |
| SciCode | — | 13.2% |

## Agentic & Tool Use

- Gemini 1.5 Flash (May 2024): 26.3 (#97)
- Llama 3.1-8B: 22.3 (#123)

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3.1-8B |
|---|---|---|
| BALROG | 14.6% | 15.1% |
| Berkeley Function Calling Leaderboard | — | 25.8% |

## Reasoning

- Gemini 1.5 Flash (May 2024): 20.8 (#212)
- Llama 3.1-8B: 14.5 (#316)

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3.1-8B |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1175 |
| DTBench | 53.8% | 50.9% |
| Epoch Capabilities Index | 129.37 | 116.48 |
| PIQA | 87.5% | 81.2% |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| LMCA | — | 5.4% |
| ForecastBench | 53.9 | — |

## Math

- Gemini 1.5 Flash (May 2024): 20.8 (#274)
- Llama 3.1-8B: 9.5 (#311)

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3.1-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.3% | 1.7% |
| Omni-MATH | 30.4% | 13.7% |
| LMArena Math | 1269 | 1179 |
| MATH Level 5 | 61.9% | 22.9% |
| GSM8K | 82.4% | 82.4% |
| FrontierMath (Feb 2025 set) | 0% | — |

## Knowledge

- Gemini 1.5 Flash (May 2024): 26.2 (#253)
- Llama 3.1-8B: 8.0 (#302)

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3.1-8B |
|---|---|---|
| GPQA Diamond | 47.3% | 27% |
| MMLU-Pro | 67.8% | 40.6% |
| GPQA (HELM) | 43.7% | 24.7% |
| LMArena Expert | 1233 | 1144 |
| BoolQ | 85.8% | 82.8% |
| MMLU | 77.9% | 56.1% |

## Multimodal

- Gemini 1.5 Flash (May 2024): 35.3 (#76)
- Llama 3.1-8B: —

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3.1-8B |
|---|---|---|
| LMArena Vision | 1141 | — |
| Video-MME | 70.3% | — |
| GeoBench | 76% | — |

## Multilingual

- Gemini 1.5 Flash (May 2024): 43.1 (#184)
- Llama 3.1-8B: 34.2 (#244)

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3.1-8B |
|---|---|---|
| LMArena Non-English | 1278 | 1148 |
| LMArena Chinese | 1295 | 1151 |
| LMArena French | 1257 | 1176 |
| LMArena German | 1262 | 1144 |
| LMArena Japanese | 1252 | 1061 |
| LMArena Korean | 1220 | 1053 |
| LMArena Russian | 1288 | 1158 |
| LMArena Spanish | 1242 | 1169 |

## Instruction Following

- Gemini 1.5 Flash (May 2024): 67.0 (#199)
- Llama 3.1-8B: 59.1 (#253)

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3.1-8B |
|---|---|---|
| IFEval | 83.1% | 74.3% |
| LMArena Instruction Following | 1258 | 1159 |

## Long Context

- Gemini 1.5 Flash (May 2024): 39.0 (#182)
- Llama 3.1-8B: 35.8 (#233)

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3.1-8B |
|---|---|---|
| LMArena Longer Query | 1284 | 1182 |

## Writing & Preference

- Gemini 1.5 Flash (May 2024): 48.9 (#190)
- Llama 3.1-8B: 29.9 (#285)

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama 3.1-8B |
|---|---|---|
| LMArena Text | 1287 | 1187 |
| LMArena Creative Writing | 1285 | 1154 |
| WildBench | 79.2% | 68.7% |
| LMArena Multi-Turn | 1253 | 1172 |
| EQ-Bench Creative Writing | — | 713 |

## FAQ

### Is Gemini 1.5 Flash (May 2024) better than Llama 3.1-8B?

Gemini 1.5 Flash (May 2024) is the stronger model overall, scoring 32.9 to 22.8 on the Noometry Index.

### Is Gemini 1.5 Flash (May 2024) or Llama 3.1-8B better for coding?

Gemini 1.5 Flash (May 2024) scores higher on coding benchmarks: 33.9 versus 19.9 in the Noometry coding category.

### How many benchmarks do Gemini 1.5 Flash (May 2024) and Llama 3.1-8B share?

37 benchmarks have published results for both models. Gemini 1.5 Flash (May 2024) has 42 scored results on Noometry and Llama 3.1-8B has 43.