# Grok 2 Mini 2024 08 13 vs Llama 3.1-70B

> Grok 2 Mini 2024 08 13 is the stronger model overall, scoring 37.0 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-2-mini-vs-llama-3-1-70b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Grok 2 Mini 2024 08 13 scores higher in 8 categories and Llama 3.1-70B in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 2 Mini 2024 08 13 leads 32.8 to 12.7.
- Llama 3.1-70B has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 2 Mini 2024 08 13 | Llama 3.1-70B |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 37.0 | 29.4 |
| Rank | 196 | 299 |
| Context | — | 128K |
| Input $/M | — | $0.40 |
| Output $/M | — | $0.40 |
| Weights | Proprietary | Open |

## Coding

- Grok 2 Mini 2024 08 13: 36.4 (#194)
- Llama 3.1-70B: 29.8 (#292)

| Benchmark | Grok 2 Mini 2024 08 13 | Llama 3.1-70B |
|---|---|---|
| LMArena Coding | 1269 | 1260 |
| WeirdML | — | 9% |
| BigCodeBench Instruct | — | 46.1% |
| BigCodeBench Complete | — | 54.8% |

## Agentic & Tool Use

- Grok 2 Mini 2024 08 13: —
- Llama 3.1-70B: 24.9 (#104)

| Benchmark | Grok 2 Mini 2024 08 13 | Llama 3.1-70B |
|---|---|---|
| TheAgentCompany | — | 6.9% |
| BALROG | — | 27.9% |

## Reasoning

- Grok 2 Mini 2024 08 13: 23.7 (#162)
- Llama 3.1-70B: 20.8 (#215)

| Benchmark | Grok 2 Mini 2024 08 13 | Llama 3.1-70B |
|---|---|---|
| LMArena Hard Prompts | 1255 | 1241 |
| DTBench | — | 60% |
| LMCA | — | 14.8% |
| Epoch Capabilities Index | — | 125.91 |

## Math

- Grok 2 Mini 2024 08 13: 32.8 (#185)
- Llama 3.1-70B: 12.7 (#298)

| Benchmark | Grok 2 Mini 2024 08 13 | Llama 3.1-70B |
|---|---|---|
| LMArena Math | 1265 | 1252 |
| OTIS Mock AIME 2024-2025 | — | 3.6% |
| Omni-MATH | — | 21% |
| MATH Level 5 | — | 36.7% |

## Knowledge

- Grok 2 Mini 2024 08 13: 33.4 (#195)
- Llama 3.1-70B: 24.1 (#264)

| Benchmark | Grok 2 Mini 2024 08 13 | Llama 3.1-70B |
|---|---|---|
| LMArena Expert | 1238 | 1209 |
| GPQA Diamond | — | 44.2% |
| MMLU-Pro | — | 65.3% |
| GPQA (HELM) | — | 42.6% |
| MMLU | — | 80.1% |

## Multilingual

- Grok 2 Mini 2024 08 13: 41.6 (#203)
- Llama 3.1-70B: 38.9 (#220)

| Benchmark | Grok 2 Mini 2024 08 13 | Llama 3.1-70B |
|---|---|---|
| LMArena Non-English | 1257 | 1219 |
| LMArena Chinese | 1262 | 1215 |
| LMArena French | 1285 | 1260 |
| LMArena German | 1273 | 1222 |
| LMArena Japanese | 1213 | 1132 |
| LMArena Korean | 1195 | 1140 |
| LMArena Russian | 1261 | 1234 |
| LMArena Spanish | 1278 | 1253 |

## Instruction Following

- Grok 2 Mini 2024 08 13: 65.7 (#215)
- Llama 3.1-70B: 65.5 (#218)

| Benchmark | Grok 2 Mini 2024 08 13 | Llama 3.1-70B |
|---|---|---|
| LMArena Instruction Following | 1245 | 1231 |
| IFEval | — | 82.1% |

## Long Context

- Grok 2 Mini 2024 08 13: 38.4 (#191)
- Llama 3.1-70B: 37.6 (#208)

| Benchmark | Grok 2 Mini 2024 08 13 | Llama 3.1-70B |
|---|---|---|
| LMArena Longer Query | 1267 | 1241 |

## Writing & Preference

- Grok 2 Mini 2024 08 13: 47.5 (#207)
- Llama 3.1-70B: 35.6 (#262)

| Benchmark | Grok 2 Mini 2024 08 13 | Llama 3.1-70B |
|---|---|---|
| LMArena Text | 1281 | 1261 |
| LMArena Creative Writing | 1242 | 1232 |
| LMArena Multi-Turn | 1265 | 1256 |
| EQ-Bench Creative Writing | — | 784 |
| WildBench | — | 75.8% |

## FAQ

### Is Grok 2 Mini 2024 08 13 better than Llama 3.1-70B?

Grok 2 Mini 2024 08 13 is the stronger model overall, scoring 37.0 to 29.4 on the Noometry Index.

### Is Grok 2 Mini 2024 08 13 or Llama 3.1-70B better for coding?

Grok 2 Mini 2024 08 13 scores higher on coding benchmarks: 36.4 versus 29.8 in the Noometry coding category.

### How many benchmarks do Grok 2 Mini 2024 08 13 and Llama 3.1-70B share?

17 benchmarks have published results for both models. Grok 2 Mini 2024 08 13 has 17 scored results on Noometry and Llama 3.1-70B has 35.