# Gemma 2 2b IT vs Llama 2-70B

> Gemma 2 2b IT is the stronger model overall, scoring 32.5 to 24.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2-2b-it-vs-llama-2-70b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Gemma 2 2b IT scores higher in 8 categories and Llama 2-70B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 2 2b IT leads 30.1 to 7.5.

## Snapshot

| | Gemma 2 2b IT | Llama 2-70B |
|---|---|---|
| Provider | Google | Meta |
| Noometry Index | 32.5 | 24.1 |
| Rank | 244 | 343 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Gemma 2 2b IT: 31.8 (#268)
- Llama 2-70B: 30.8 (#281)

| Benchmark | Gemma 2 2b IT | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1112 | 1079 |

## Reasoning

- Gemma 2 2b IT: 20.5 (#219)
- Llama 2-70B: 13.7 (#324)

| Benchmark | Gemma 2 2b IT | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1073 |
| DTBench | — | 41.6% |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| Epoch Capabilities Index | — | 113.59 |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |

## Math

- Gemma 2 2b IT: 30.1 (#212)
- Llama 2-70B: 7.5 (#320)

| Benchmark | Gemma 2 2b IT | Llama 2-70B |
|---|---|---|
| LMArena Math | 1135 | 1091 |
| OTIS Mock AIME 2024-2025 | — | 0% |
| MATH Level 5 | — | 3.3% |
| GSM8K | — | 69.6% |

## Knowledge

- Gemma 2 2b IT: 29.3 (#229)
- Llama 2-70B: 7.4 (#305)

| Benchmark | Gemma 2 2b IT | Llama 2-70B |
|---|---|---|
| LMArena Expert | 1096 | 1039 |
| GPQA Diamond | — | 26.3% |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |

## Multilingual

- Gemma 2 2b IT: 32.5 (#252)
- Llama 2-70B: 27.9 (#269)

| Benchmark | Gemma 2 2b IT | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1121 | 1045 |
| LMArena Chinese | 1132 | 994 |
| LMArena French | 1156 | 1089 |
| LMArena German | 1114 | 1041 |
| LMArena Japanese | 1083 | 927 |
| LMArena Korean | 1055 | 964 |
| LMArena Russian | 1118 | 1083 |
| LMArena Spanish | 1140 | 1142 |

## Instruction Following

- Gemma 2 2b IT: 58.1 (#258)
- Llama 2-70B: 55.1 (#273)

| Benchmark | Gemma 2 2b IT | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1118 | 1071 |

## Long Context

- Gemma 2 2b IT: 34.2 (#245)
- Llama 2-70B: 32.2 (#265)

| Benchmark | Gemma 2 2b IT | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1130 | 1062 |

## Writing & Preference

- Gemma 2 2b IT: 36.6 (#258)
- Llama 2-70B: 32.5 (#274)

| Benchmark | Gemma 2 2b IT | Llama 2-70B |
|---|---|---|
| LMArena Text | 1156 | 1115 |
| LMArena Creative Writing | 1147 | 1075 |
| LMArena Multi-Turn | 1118 | 1088 |

## FAQ

### Is Gemma 2 2b IT better than Llama 2-70B?

Gemma 2 2b IT is the stronger model overall, scoring 32.5 to 24.1 on the Noometry Index.

### Is Gemma 2 2b IT or Llama 2-70B better for coding?

They score almost the same on coding (31.8 vs 30.8); test both on your own repository before choosing.

### How many benchmarks do Gemma 2 2b IT and Llama 2-70B share?

17 benchmarks have published results for both models. Gemma 2 2b IT has 17 scored results on Noometry and Llama 2-70B has 35.