# Grok-2 (Dec 2024) vs Llama 3.1-8B

> Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 23.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-2-vs-llama-3-1-8b
- Last updated: 2026-10-10
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 8 categories and Llama 3.1-8B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok-2 (Dec 2024) leads 29.8 to 8.0.
- The biggest single-benchmark swing is MATH Level 5: 63.5% for Grok-2 (Dec 2024) and 22.9% for Llama 3.1-8B.
- Llama 3.1-8B has downloadable open weights; the other is API-only.

## Snapshot

| | Grok-2 (Dec 2024) | Llama 3.1-8B |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 33.7 | 23.0 |
| Rank | 239 | 352 |
| Context | — | 128K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.08 |
| Weights | Proprietary | Open |

## Coding

- Grok-2 (Dec 2024): 33.3 (#258)
- Llama 3.1-8B: 20.2 (#340)

| Benchmark | Grok-2 (Dec 2024) | Llama 3.1-8B |
|---|---|---|
| WeirdML | 22.2% | 1.7% |
| LMArena Coding | 1287 | 1195 |
| SciCode | — | 13.2% |
| BigCodeBench Instruct | — | 32.8% |
| LiveBench Coding | 46.4% | — |
| BigCodeBench Complete | — | 40.5% |
| HumanEval+ | — | 62.8% |
| MBPP+ | — | 55.6% |

## Agentic & Tool Use

- Grok-2 (Dec 2024): —
- Llama 3.1-8B: 22.5 (#131)

| Benchmark | Grok-2 (Dec 2024) | Llama 3.1-8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 25.8% |
| BALROG | — | 15.1% |

## Reasoning

- Grok-2 (Dec 2024): 16.9 (#299)
- Llama 3.1-8B: 14.9 (#321)

| Benchmark | Grok-2 (Dec 2024) | Llama 3.1-8B |
|---|---|---|
| LMArena Hard Prompts | 1272 | 1175 |
| DTBench | 65.2% | 50.9% |
| Epoch Capabilities Index | 130.48 | 116.57 |
| SimpleBench | 22.7% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 54.8% | — |
| LiveBench Data Analysis | 54.5% | — |
| LMCA | — | 5.4% |
| LiveBench | 54.3% | — |
| PIQA | — | 81.2% |

## Math

- Grok-2 (Dec 2024): 20.8 (#284)
- Llama 3.1-8B: 10.2 (#317)

| Benchmark | Grok-2 (Dec 2024) | Llama 3.1-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 11.5% | 1.7% |
| LMArena Math | 1283 | 1179 |
| MATH Level 5 | 63.5% | 22.9% |
| Omni-MATH | — | 13.7% |
| LiveBench Math | 54.9% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
| GSM8K | — | 82.4% |

## Knowledge

- Grok-2 (Dec 2024): 29.8 (#233)
- Llama 3.1-8B: 8.0 (#307)

| Benchmark | Grok-2 (Dec 2024) | Llama 3.1-8B |
|---|---|---|
| GPQA Diamond | 53.8% | 27% |
| LMArena Expert | 1254 | 1144 |
| MMLU-Pro | — | 40.6% |
| Confabulations | 20.1% | — |
| GPQA (HELM) | — | 24.7% |
| BoolQ | — | 82.8% |
| MMLU | — | 56.1% |

## Multilingual

- Grok-2 (Dec 2024): 43.1 (#188)
- Llama 3.1-8B: 34.0 (#249)

| Benchmark | Grok-2 (Dec 2024) | Llama 3.1-8B |
|---|---|---|
| LMArena Non-English | 1282 | 1148 |
| LMArena Chinese | 1289 | 1151 |
| LMArena French | 1318 | 1177 |
| LMArena German | 1287 | 1144 |
| LMArena Japanese | 1244 | 1061 |
| LMArena Korean | 1237 | 1053 |
| LMArena Russian | 1286 | 1158 |
| LMArena Spanish | 1281 | 1169 |

## Instruction Following

- Grok-2 (Dec 2024): 66.9 (#202)
- Llama 3.1-8B: 58.9 (#258)

| Benchmark | Grok-2 (Dec 2024) | Llama 3.1-8B |
|---|---|---|
| LMArena Instruction Following | 1270 | 1159 |
| LiveBench Instruction Following | 69.6% | — |
| IFEval | — | 74.3% |

## Long Context

- Grok-2 (Dec 2024): 38.8 (#190)
- Llama 3.1-8B: 35.8 (#238)

| Benchmark | Grok-2 (Dec 2024) | Llama 3.1-8B |
|---|---|---|
| LMArena Longer Query | 1276 | 1182 |

## Writing & Preference

- Grok-2 (Dec 2024): 48.6 (#198)
- Llama 3.1-8B: 29.7 (#290)

| Benchmark | Grok-2 (Dec 2024) | Llama 3.1-8B |
|---|---|---|
| LMArena Text | 1305 | 1187 |
| LMArena Creative Writing | 1284 | 1154 |
| LMArena Multi-Turn | 1290 | 1172 |
| Short-Story Creative Writing | 63.6% | — |
| EQ-Bench Creative Writing | — | 713 |
| WildBench | — | 68.7% |
| LiveBench Language | 45.6% | — |

## FAQ

### Is Grok-2 (Dec 2024) better than Llama 3.1-8B?

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 23.0 on the Noometry Index.

### Is Grok-2 (Dec 2024) or Llama 3.1-8B better for coding?

Grok-2 (Dec 2024) scores higher on coding benchmarks: 33.3 versus 20.2 in the Noometry coding category.

### How many benchmarks do Grok-2 (Dec 2024) and Llama 3.1-8B share?

23 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Llama 3.1-8B has 43.