# Gemini 1.5 Flash (May 2024) vs Llama-3.3-70B-Instruct

> Gemini 1.5 Flash (May 2024) is the stronger model overall, scoring 32.9 to 30.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-1-5-flash-vs-llama-3-3-70b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 28

## Summary

- They share 28 benchmarks with published results for both. Gemini 1.5 Flash (May 2024) scores higher in 7 categories and Llama-3.3-70B-Instruct in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Gemini 1.5 Flash (May 2024) leads 39.0 to 26.4.
- The biggest single-benchmark swing is MATH Level 5: 61.9% for Gemini 1.5 Flash (May 2024) and 41.6% for Llama-3.3-70B-Instruct.
- Llama-3.3-70B-Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 1.5 Flash (May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| Provider | Google | Meta |
| Noometry Index | 32.9 | 30.3 |
| Rank | 240 | 283 |
| Context | — | 128K |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.32 |
| Weights | Proprietary | Open |

## Coding

- Gemini 1.5 Flash (May 2024): 33.9 (#233)
- Llama-3.3-70B-Instruct: 30.6 (#284)

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| WeirdML | 24.9% | 14.4% |
| BigCodeBench Instruct | 43.5% | 46.9% |
| LMArena Coding | 1262 | 1268 |
| BigCodeBench Complete | 55.1% | 57.5% |
| SciCode | — | 26% |
| LiveBench Coding | — | 36.6% |
| HumanEval+ | 75.6% | — |
| MBPP+ | 67.5% | — |

## Agentic & Tool Use

- Gemini 1.5 Flash (May 2024): 26.3 (#97)
- Llama-3.3-70B-Instruct: 25.6 (#100)

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| BALROG | 14.6% | 23% |
| Berkeley Function Calling Leaderboard | — | 31.9% |

## Reasoning

- Gemini 1.5 Flash (May 2024): 20.8 (#212)
- Llama-3.3-70B-Instruct: 13.7 (#325)

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1257 |
| DTBench | 53.8% | 59.5% |
| Epoch Capabilities Index | 129.37 | 127.32 |
| ForecastBench | 53.9 | 58.6 |
| SimpleBench | — | 19.9% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 50.8% |
| LiveBench Data Analysis | — | 49.5% |
| LMCA | — | 17.5% |
| LiveBench | — | 50.2% |
| PIQA | 87.5% | — |

## Math

- Gemini 1.5 Flash (May 2024): 20.8 (#274)
- Llama-3.3-70B-Instruct: 14.3 (#292)

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.3% | 5.1% |
| LMArena Math | 1269 | 1268 |
| MATH Level 5 | 61.9% | 41.6% |
| Omni-MATH | 30.4% | — |
| LiveBench Math | — | 42.2% |
| FrontierMath (Feb 2025 set) | 0% | — |
| GSM8K | 82.4% | — |

## Knowledge

- Gemini 1.5 Flash (May 2024): 26.2 (#253)
- Llama-3.3-70B-Instruct: 30.5 (#220)

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| GPQA Diamond | 47.3% | 47.4% |
| LMArena Expert | 1233 | 1225 |
| MMLU | 77.9% | 86.3% |
| MMLU-Pro | 67.8% | — |
| Confabulations | — | 22.8% |
| Vectara Hallucination Rate | — | 4.1% |
| GPQA (HELM) | 43.7% | — |
| BoolQ | 85.8% | — |

## Multimodal

- Gemini 1.5 Flash (May 2024): 35.3 (#76)
- Llama-3.3-70B-Instruct: —

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Vision | 1141 | — |
| Video-MME | 70.3% | — |
| GeoBench | 76% | — |

## Multilingual

- Gemini 1.5 Flash (May 2024): 43.1 (#184)
- Llama-3.3-70B-Instruct: 40.1 (#215)

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Non-English | 1278 | 1236 |
| LMArena Chinese | 1295 | 1217 |
| LMArena French | 1257 | 1280 |
| LMArena German | 1262 | 1251 |
| LMArena Japanese | 1252 | 1149 |
| LMArena Korean | 1220 | 1142 |
| LMArena Russian | 1288 | 1252 |
| LMArena Spanish | 1242 | 1269 |

## Instruction Following

- Gemini 1.5 Flash (May 2024): 67.0 (#199)
- Llama-3.3-70B-Instruct: 71.3 (#152)

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Instruction Following | 1258 | 1242 |
| LiveBench Instruction Following | — | 82.7% |
| IFEval | 83.1% | — |

## Long Context

- Gemini 1.5 Flash (May 2024): 39.0 (#182)
- Llama-3.3-70B-Instruct: 26.4 (#290)

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Longer Query | 1284 | 1256 |
| Fiction.LiveBench | — | 33.3% |

## Writing & Preference

- Gemini 1.5 Flash (May 2024): 48.9 (#190)
- Llama-3.3-70B-Instruct: 47.8 (#203)

| Benchmark | Gemini 1.5 Flash (May 2024) | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Text | 1287 | 1274 |
| LMArena Creative Writing | 1285 | 1250 |
| LMArena Multi-Turn | 1253 | 1279 |
| WildBench | 79.2% | — |
| LiveBench Language | — | 39.2% |

## FAQ

### Is Gemini 1.5 Flash (May 2024) better than Llama-3.3-70B-Instruct?

Gemini 1.5 Flash (May 2024) is the stronger model overall, scoring 32.9 to 30.3 on the Noometry Index.

### Is Gemini 1.5 Flash (May 2024) or Llama-3.3-70B-Instruct better for coding?

Gemini 1.5 Flash (May 2024) scores higher on coding benchmarks: 33.9 versus 30.6 in the Noometry coding category.

### How many benchmarks do Gemini 1.5 Flash (May 2024) and Llama-3.3-70B-Instruct share?

28 benchmarks have published results for both models. Gemini 1.5 Flash (May 2024) has 42 scored results on Noometry and Llama-3.3-70B-Instruct has 43.