# Grok-3 mini vs Llama 3.1-8B

> Grok-3 mini is the stronger model overall, scoring 41.0 to 22.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-3-mini-vs-llama-3-1-8b
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Grok-3 mini scores higher in 7 categories and Llama 3.1-8B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok-3 mini leads 46.3 to 8.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 1.7% for Llama 3.1-8B.
- Llama 3.1-8B has downloadable open weights; the other is API-only.

## Snapshot

| | Grok-3 mini | Llama 3.1-8B |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 41.0 | 22.8 |
| Rank | 130 | 347 |
| Context | — | 128K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.08 |
| Weights | Proprietary | Open |

## Coding

- Grok-3 mini: 40.4 (#126)
- Llama 3.1-8B: 19.9 (#335)

| Benchmark | Grok-3 mini | Llama 3.1-8B |
|---|---|---|
| WeirdML | 42.6% | 1.7% |
| LMArena Coding | 1380 | 1195 |
| Aider Polyglot | 49.3% | — |
| SciCode | — | 13.2% |
| BigCodeBench Instruct | — | 32.8% |
| BigCodeBench Complete | — | 40.5% |
| HumanEval+ | — | 62.8% |
| MBPP+ | — | 55.6% |

## Agentic & Tool Use

- Grok-3 mini: —
- Llama 3.1-8B: 22.3 (#123)

| Benchmark | Grok-3 mini | Llama 3.1-8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 25.8% |
| BALROG | — | 15.1% |

## Reasoning

- Grok-3 mini: 13.8 (#323)
- Llama 3.1-8B: 14.5 (#316)

| Benchmark | Grok-3 mini | Llama 3.1-8B |
|---|---|---|
| LMArena Hard Prompts | 1374 | 1175 |
| Epoch Capabilities Index | 140.35 | 116.48 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| DTBench | — | 50.9% |
| LMCA | — | 5.4% |
| PIQA | — | 81.2% |

## Math

- Grok-3 mini: 40.3 (#78)
- Llama 3.1-8B: 9.5 (#311)

| Benchmark | Grok-3 mini | Llama 3.1-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 1.7% |
| Omni-MATH | 31.8% | 13.7% |
| LMArena Math | 1386 | 1179 |
| MATH Level 5 | 90.9% | 22.9% |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| GSM8K | — | 82.4% |

## Knowledge

- Grok-3 mini: 46.3 (#75)
- Llama 3.1-8B: 8.0 (#302)

| Benchmark | Grok-3 mini | Llama 3.1-8B |
|---|---|---|
| GPQA Diamond | 76.3% | 27% |
| MMLU-Pro | 79.9% | 40.6% |
| GPQA (HELM) | 67.5% | 24.7% |
| LMArena Expert | 1395 | 1144 |
| Confabulations | 10.8% | — |
| BoolQ | — | 82.8% |
| MMLU | — | 56.1% |

## Multilingual

- Grok-3 mini: 48.3 (#141)
- Llama 3.1-8B: 34.2 (#244)

| Benchmark | Grok-3 mini | Llama 3.1-8B |
|---|---|---|
| LMArena Non-English | 1352 | 1148 |
| LMArena Chinese | 1387 | 1151 |
| LMArena French | 1357 | 1176 |
| LMArena German | 1350 | 1144 |
| LMArena Japanese | 1343 | 1061 |
| LMArena Korean | 1336 | 1053 |
| LMArena Russian | 1352 | 1158 |
| LMArena Spanish | 1379 | 1169 |

## Instruction Following

- Grok-3 mini: 78.7 (#8)
- Llama 3.1-8B: 59.1 (#253)

| Benchmark | Grok-3 mini | Llama 3.1-8B |
|---|---|---|
| IFEval | 95.1% | 74.3% |
| LMArena Instruction Following | 1356 | 1159 |

## Long Context

- Grok-3 mini: 41.0 (#142)
- Llama 3.1-8B: 35.8 (#233)

| Benchmark | Grok-3 mini | Llama 3.1-8B |
|---|---|---|
| LMArena Longer Query | 1372 | 1182 |
| Fiction.LiveBench | 66.7% | — |

## Writing & Preference

- Grok-3 mini: 52.7 (#163)
- Llama 3.1-8B: 29.9 (#285)

| Benchmark | Grok-3 mini | Llama 3.1-8B |
|---|---|---|
| LMArena Text | 1370 | 1187 |
| LMArena Creative Writing | 1342 | 1154 |
| WildBench | 65.1% | 68.7% |
| LMArena Multi-Turn | 1355 | 1172 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | — | 713 |

## FAQ

### Is Grok-3 mini better than Llama 3.1-8B?

Grok-3 mini is the stronger model overall, scoring 41.0 to 22.8 on the Noometry Index.

### Is Grok-3 mini or Llama 3.1-8B better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.4 versus 19.9 in the Noometry coding category.

### How many benchmarks do Grok-3 mini and Llama 3.1-8B share?

27 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Llama 3.1-8B has 43.