Model comparison
Llama 2-13B vs Mixtral 8x22B
Llama 2-13B is the stronger model overall, scoring 29.6 to 27.1 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 3 categories and Mixtral 8x22B in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 2-13B leads 28.1 to 15.1.
- The biggest single-benchmark swing is DTBench: 42.2% for Llama 2-13B and 55.1% for Mixtral 8x22B.
Side by side
| Llama 2-13B | Mixtral 8x22B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 29.6 | 27.1 |
| Released | 2023-07-18 | 2024-04-17 |
| Weights | Open | Open |
| Context window | — | 64K |
| Max output | — | 64K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 32 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-13B leads
Llama 2-13B: 30.9 (#291), Mixtral 8x22B: 24.2 (#329)
| Benchmark | Llama 2-13B | Mixtral 8x22B |
|---|---|---|
| LMArena Coding | 1062 | 1166 |
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use Not comparable
Llama 2-13B: —, Mixtral 8x22B: 23.1 (#127)
| Benchmark | Llama 2-13B | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |
Reasoning Mixtral 8x22B leads
Llama 2-13B: 12.8 (#337), Mixtral 8x22B: 19.9 (#248)
| Benchmark | Llama 2-13B | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1150 |
| DTBench | 42.2% | 55.1% |
| Epoch Capabilities Index | 106.17 | 122.03 |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | 58.2% | — |
| ForecastBench | — | 56.3 |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |
Math Llama 2-13B leads
Llama 2-13B: 31.1 (#229), Mixtral 8x22B: 22.9 (#275)
| Benchmark | Llama 2-13B | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1065 | 1184 |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |
| GSM8K | 36.9% | — |
Knowledge Llama 2-13B leads
Llama 2-13B: 28.1 (#249), Mixtral 8x22B: 15.1 (#293)
| Benchmark | Llama 2-13B | Mixtral 8x22B |
|---|---|---|
| LMArena Expert | 1030 | 1113 |
| MMLU | 55.6% | 77.8% |
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| GPQA (HELM) | — | 33.4% |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, Mixtral 8x22B: —
| Benchmark | Llama 2-13B | Mixtral 8x22B |
|---|---|---|
| ScienceQA | 55.8% | — |
Multilingual Mixtral 8x22B leads
Llama 2-13B: 26.5 (#279), Mixtral 8x22B: 32.8 (#255)
| Benchmark | Llama 2-13B | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1024 | 1128 |
| LMArena Chinese | 1001 | 1116 |
| LMArena French | 1044 | 1166 |
| LMArena German | 1009 | 1141 |
| LMArena Japanese | 894 | 1037 |
| LMArena Korean | 953 | 1057 |
| LMArena Russian | 1055 | 1158 |
| LMArena Spanish | 1087 | 1151 |
Instruction Following Mixtral 8x22B leads
Llama 2-13B: 53.3 (#287), Mixtral 8x22B: 57.7 (#266)
| Benchmark | Llama 2-13B | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1045 | 1147 |
| IFEval | — | 72.4% |
Long Context Mixtral 8x22B leads
Llama 2-13B: 32.3 (#269), Mixtral 8x22B: 34.7 (#247)
| Benchmark | Llama 2-13B | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1064 | 1144 |
Writing & Preference Mixtral 8x22B leads
Llama 2-13B: 29.8 (#289), Mixtral 8x22B: 36.9 (#262)
| Benchmark | Llama 2-13B | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1084 | 1162 |
| LMArena Creative Writing | 1047 | 1141 |
| LMArena Multi-Turn | 1050 | 1130 |
| WildBench | — | 71.1% |
Frequently asked questions
Is Llama 2-13B better than Mixtral 8x22B?
Llama 2-13B is the stronger model overall, scoring 29.6 to 27.1 on the Noometry Index.
Is Llama 2-13B or Mixtral 8x22B better for coding?
Llama 2-13B scores higher on coding benchmarks: 30.9 versus 24.2 in the Noometry coding category.
How many benchmarks do Llama 2-13B and Mixtral 8x22B share?
20 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Mixtral 8x22B has 34.