Model comparison
Grok-3 mini vs Llama 13b
Grok-3 mini is the stronger model overall, scoring 41.2 to 24.4 on the Noometry Index.
Last verified . 9 shared benchmarks.
MetaSummary
- They share 9 benchmarks with published results for both. Grok-3 mini scores higher in 5 categories and Llama 13b in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Grok-3 mini leads 78.5 to 36.7.
- Llama 13b has downloadable open weights; the other is API-only.
Side by side
| Grok-3 mini | Llama 13b | |
|---|---|---|
| Provider | xAI | Meta |
| Noometry Index | 41.2 | 24.4 |
| Released | 2025-04-09 | 2023-02-24 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Grok-3 mini: 40.8 (#131), Llama 13b: 21.4 (#337)
| Benchmark | Grok-3 mini | Llama 13b |
|---|---|---|
| LMArena Coding | 1379 | 683 |
| Aider Polyglot | 49.3% | — |
| WeirdML | 42.6% | — |
Reasoning Too close to call
Grok-3 mini: 13.6 (#334), Llama 13b: 14.0 (#329)
| Benchmark | Grok-3 mini | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1375 | 728 |
| Epoch Capabilities Index | 140.35 | 100.58 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| BIG-Bench Hard | — | 37.9% |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |
Math Grok-3 mini leads
Grok-3 mini: 42.1 (#85), Llama 13b: 26.7 (#256)
| Benchmark | Grok-3 mini | Llama 13b |
|---|---|---|
| LMArena Math | 1386 | 838 |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| GSM8K | — | 20.6% |
Knowledge Not comparable
Grok-3 mini: 46.4 (#81), Llama 13b: —
| Benchmark | Grok-3 mini | Llama 13b |
|---|---|---|
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
| LMArena Expert | 1395 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
Grok-3 mini: —, Llama 13b: —
| Benchmark | Grok-3 mini | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |
Multilingual Grok-3 mini leads
Grok-3 mini: 48.1 (#145), Llama 13b: 16.6 (#297)
| Benchmark | Grok-3 mini | Llama 13b |
|---|---|---|
| LMArena Non-English | 1352 | 819 |
| LMArena Chinese | 1387 | — |
| LMArena French | 1357 | — |
| LMArena German | 1349 | — |
| LMArena Japanese | 1342 | — |
| LMArena Korean | 1335 | — |
| LMArena Russian | 1353 | — |
| LMArena Spanish | 1381 | — |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.5 (#9), Llama 13b: 36.7 (#305)
| Benchmark | Grok-3 mini | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1357 | 781 |
| IFEval | 95.1% | — |
Long Context Not comparable
Grok-3 mini: 41.0 (#147), Llama 13b: —
| Benchmark | Grok-3 mini | Llama 13b |
|---|---|---|
| Fiction.LiveBench | 66.7% | — |
| LMArena Longer Query | 1372 | — |
Writing & Preference Grok-3 mini leads
Grok-3 mini: 52.5 (#169), Llama 13b: 13.8 (#312)
| Benchmark | Grok-3 mini | Llama 13b |
|---|---|---|
| LMArena Text | 1370 | 834 |
| LMArena Creative Writing | 1342 | 794 |
| LMArena Multi-Turn | 1355 | 753 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
Frequently asked questions
Is Grok-3 mini better than Llama 13b?
Grok-3 mini is the stronger model overall, scoring 41.2 to 24.4 on the Noometry Index.
Is Grok-3 mini or Llama 13b better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.8 versus 21.4 in the Noometry coding category.
How many benchmarks do Grok-3 mini and Llama 13b share?
9 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Llama 13b has 21.