# Grok-3 mini vs Llama 3.1-405B

> Grok-3 mini is the stronger model overall, scoring 41.0 to 30.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-3-mini-vs-llama-3-1-405b
- Last updated: 2026-10-10
- Shared benchmarks: 29

## Summary

- They share 29 benchmarks with published results for both. Grok-3 mini scores higher in 7 categories and Llama 3.1-405B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok-3 mini leads 40.3 to 17.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 9.7% for Llama 3.1-405B.
- Llama 3.1-405B has downloadable open weights; the other is API-only.

## Snapshot

| | Grok-3 mini | Llama 3.1-405B |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 41.0 | 30.4 |
| Rank | 130 | 279 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Grok-3 mini: 40.4 (#126)
- Llama 3.1-405B: 32.7 (#257)

| Benchmark | Grok-3 mini | Llama 3.1-405B |
|---|---|---|
| WeirdML | 42.6% | 21.4% |
| LMArena Coding | 1380 | 1291 |
| Aider Polyglot | 49.3% | — |

## Agentic & Tool Use

- Grok-3 mini: —
- Llama 3.1-405B: 20.9 (#131)

| Benchmark | Grok-3 mini | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |

## Reasoning

- Grok-3 mini: 13.8 (#323)
- Llama 3.1-405B: 16.4 (#293)

| Benchmark | Grok-3 mini | Llama 3.1-405B |
|---|---|---|
| Kagi LLM Benchmark | 61.3% | 45% |
| LMArena Hard Prompts | 1374 | 1270 |
| Epoch Capabilities Index | 140.35 | 128.76 |
| ARC-AGI-2 | 0.4% | — |
| SimpleBench | — | 23% |
| ARC-AGI-1 | 16.5% | — |
| DTBench | — | 61.4% |
| BIG-Bench Hard | — | 82.9% |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |

## Math

- Grok-3 mini: 40.3 (#78)
- Llama 3.1-405B: 17.3 (#283)

| Benchmark | Grok-3 mini | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 9.7% |
| Omni-MATH | 31.8% | 24.9% |
| LMArena Math | 1386 | 1281 |
| MATH Level 5 | 90.9% | 49.8% |
| FrontierMath (Feb 2025 set) | 5.9% | — |

## Knowledge

- Grok-3 mini: 46.3 (#75)
- Llama 3.1-405B: 30.4 (#221)

| Benchmark | Grok-3 mini | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | 76.3% | 50.9% |
| MMLU-Pro | 79.9% | 72.3% |
| Confabulations | 10.8% | 17.6% |
| GPQA (HELM) | 67.5% | 52.2% |
| LMArena Expert | 1395 | 1243 |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |

## Multilingual

- Grok-3 mini: 48.3 (#141)
- Llama 3.1-405B: 40.9 (#209)

| Benchmark | Grok-3 mini | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1352 | 1248 |
| LMArena Chinese | 1387 | 1242 |
| LMArena French | 1357 | 1278 |
| LMArena German | 1350 | 1252 |
| LMArena Japanese | 1343 | 1208 |
| LMArena Korean | 1336 | 1184 |
| LMArena Russian | 1352 | 1265 |
| LMArena Spanish | 1379 | 1259 |

## Instruction Following

- Grok-3 mini: 78.7 (#8)
- Llama 3.1-405B: 66.1 (#209)

| Benchmark | Grok-3 mini | Llama 3.1-405B |
|---|---|---|
| IFEval | 95.1% | 81.1% |
| LMArena Instruction Following | 1356 | 1259 |

## Long Context

- Grok-3 mini: 41.0 (#142)
- Llama 3.1-405B: 38.4 (#192)

| Benchmark | Grok-3 mini | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1372 | 1266 |
| Fiction.LiveBench | 66.7% | — |

## Writing & Preference

- Grok-3 mini: 52.7 (#163)
- Llama 3.1-405B: 39.1 (#246)

| Benchmark | Grok-3 mini | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1370 | 1284 |
| LMArena Creative Writing | 1342 | 1262 |
| WildBench | 65.1% | 78.3% |
| LMArena Multi-Turn | 1355 | 1297 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | — | 870 |

## FAQ

### Is Grok-3 mini better than Llama 3.1-405B?

Grok-3 mini is the stronger model overall, scoring 41.0 to 30.4 on the Noometry Index.

### Is Grok-3 mini or Llama 3.1-405B better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.4 versus 32.7 in the Noometry coding category.

### How many benchmarks do Grok-3 mini and Llama 3.1-405B share?

29 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Llama 3.1-405B has 42.