Model comparison
Llama 2-13B vs Mistral Large
Mistral Large is the stronger model overall, scoring 31.9 to 29.6 on the Noometry Index.
Last verified . 20 shared benchmarks.
Meta
Mistral AISummary
- They share 20 benchmarks with published results for both. Llama 2-13B scores higher in 1 category and Mistral Large in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Mistral Large leads 67.9 to 53.3.
- The biggest single-benchmark swing is DTBench: 42.2% for Llama 2-13B and 65.1% for Mistral Large.
Side by side
| Llama 2-13B | Mistral Large | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 29.6 | 31.9 |
| Released | 2023-07-18 | 2024-02-26 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 32 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
Llama 2-13B: 30.9 (#291), Mistral Large: 34.3 (#240)
| Benchmark | Llama 2-13B | Mistral Large |
|---|---|---|
| LMArena Coding | 1062 | 1277 |
| SciCode | — | 36.2% |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Not comparable
Llama 2-13B: —, Mistral Large: 28.6 (#89)
| Benchmark | Llama 2-13B | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
Reasoning Mistral Large leads
Llama 2-13B: 12.8 (#337), Mistral Large: 15.8 (#310)
| Benchmark | Llama 2-13B | Mistral Large |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1257 |
| DTBench | 42.2% | 65.1% |
| Epoch Capabilities Index | 106.17 | 128.52 |
| SimpleBench | — | 22.5% |
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 43.5% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| BIG-Bench Hard | 58.2% | — |
| ForecastBench | — | 57.1 |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| LiveBench | — | 48.4% |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |
Math Llama 2-13B leads
Llama 2-13B: 31.1 (#229), Mistral Large: 18.2 (#291)
| Benchmark | Llama 2-13B | Mistral Large |
|---|---|---|
| LMArena Math | 1065 | 1262 |
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
| GSM8K | 36.9% | — |
Knowledge Mistral Large leads
Llama 2-13B: 28.1 (#249), Mistral Large: 30.1 (#230)
| Benchmark | Llama 2-13B | Mistral Large |
|---|---|---|
| LMArena Expert | 1030 | 1232 |
| MMLU | 55.6% | 80% |
| GPQA Diamond | — | 51.3% |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, Mistral Large: —
| Benchmark | Llama 2-13B | Mistral Large |
|---|---|---|
| ScienceQA | 55.8% | — |
Multilingual Mistral Large leads
Llama 2-13B: 26.5 (#279), Mistral Large: 40.0 (#219)
| Benchmark | Llama 2-13B | Mistral Large |
|---|---|---|
| LMArena Non-English | 1024 | 1237 |
| LMArena Chinese | 1001 | 1240 |
| LMArena French | 1044 | 1325 |
| LMArena German | 1009 | 1254 |
| LMArena Japanese | 894 | 1188 |
| LMArena Korean | 953 | 1202 |
| LMArena Russian | 1055 | 1257 |
| LMArena Spanish | 1087 | 1268 |
Instruction Following Mistral Large leads
Llama 2-13B: 53.3 (#287), Mistral Large: 67.9 (#191)
| Benchmark | Llama 2-13B | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1045 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context Mistral Large leads
Llama 2-13B: 32.3 (#269), Mistral Large: 38.3 (#199)
| Benchmark | Llama 2-13B | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1064 | 1261 |
Writing & Preference Mistral Large leads
Llama 2-13B: 29.8 (#289), Mistral Large: 40.7 (#242)
| Benchmark | Llama 2-13B | Mistral Large |
|---|---|---|
| LMArena Text | 1084 | 1266 |
| LMArena Creative Writing | 1047 | 1243 |
| LMArena Multi-Turn | 1050 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Llama 2-13B better than Mistral Large?
Mistral Large is the stronger model overall, scoring 31.9 to 29.6 on the Noometry Index.
Is Llama 2-13B or Mistral Large better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 30.9 in the Noometry coding category.
How many benchmarks do Llama 2-13B and Mistral Large share?
20 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Mistral Large has 51.