Model comparison
Llama 2-13B vs Ministral 8B
Llama 2-13B is the stronger model overall, scoring 29.1 to 27.8 on the Noometry Index.
Last verified . 13 shared benchmarks.
Meta
Mistral AISummary
- They share 13 benchmarks with published results for both. Llama 2-13B scores higher in 2 categories and Ministral 8B in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 2-13B leads 27.5 to 12.5.
Side by side
| Llama 2-13B | Ministral 8B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 29.1 | 27.8 |
| Released | 2023-07-18 | 2024-10-01 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.10 |
| Results tracked | 32 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
Llama 2-13B: 30.4 (#287), Ministral 8B: 34.4 (#226)
| Benchmark | Llama 2-13B | Ministral 8B |
|---|---|---|
| LMArena Coding | 1062 | 1202 |
Agentic & Tool Use Not comparable
Llama 2-13B: —, Ministral 8B: 16.2 (#140)
| Benchmark | Llama 2-13B | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
Reasoning Ministral 8B leads
Llama 2-13B: 12.3 (#333), Ministral 8B: 17.7 (#279)
| Benchmark | Llama 2-13B | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1191 |
| DTBench | 42.2% | 45.7% |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | 58.2% | — |
| Epoch Capabilities Index | 105.8 | — |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |
Math Llama 2-13B leads
Llama 2-13B: 28.7 (#226), Ministral 8B: 23.7 (#262)
| Benchmark | Llama 2-13B | Ministral 8B |
|---|---|---|
| LMArena Math | 1065 | 1188 |
| MATH Level 5 | — | 14.9% |
| GSM8K | 36.9% | — |
Knowledge Llama 2-13B leads
Llama 2-13B: 27.5 (#244), Ministral 8B: 12.5 (#292)
| Benchmark | Llama 2-13B | Ministral 8B |
|---|---|---|
| LMArena Expert | 1030 | 1170 |
| GPQA Diamond | — | 27.1% |
| Vectara Hallucination Rate | — | 7.4% |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| MMLU | 55.6% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, Ministral 8B: —
| Benchmark | Llama 2-13B | Ministral 8B |
|---|---|---|
| ScienceQA | 55.8% | — |
Multilingual Ministral 8B leads
Llama 2-13B: 26.7 (#274), Ministral 8B: 35.3 (#242)
| Benchmark | Llama 2-13B | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1024 | 1165 |
| LMArena Chinese | 1001 | 1193 |
| LMArena Russian | 1055 | 1195 |
| LMArena French | 1043 | — |
| LMArena German | 1009 | — |
| LMArena Japanese | 894 | — |
| LMArena Korean | 953 | — |
| LMArena Spanish | 1086 | — |
Instruction Following Ministral 8B leads
Llama 2-13B: 53.5 (#282), Ministral 8B: 60.7 (#245)
| Benchmark | Llama 2-13B | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1046 | 1161 |
Long Context Ministral 8B leads
Llama 2-13B: 32.3 (#264), Ministral 8B: 36.7 (#222)
| Benchmark | Llama 2-13B | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1064 | 1212 |
Writing & Preference Ministral 8B leads
Llama 2-13B: 30.0 (#284), Ministral 8B: 39.8 (#241)
| Benchmark | Llama 2-13B | Ministral 8B |
|---|---|---|
| LMArena Text | 1085 | 1191 |
| LMArena Creative Writing | 1047 | 1175 |
| LMArena Multi-Turn | 1050 | 1166 |
Frequently asked questions
Is Llama 2-13B better than Ministral 8B?
Llama 2-13B is the stronger model overall, scoring 29.1 to 27.8 on the Noometry Index.
Is Llama 2-13B or Ministral 8B better for coding?
Ministral 8B scores higher on coding benchmarks: 34.4 versus 30.4 in the Noometry coding category.
How many benchmarks do Llama 2-13B and Ministral 8B share?
13 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Ministral 8B has 17.