Model comparison
Llama 2-34B vs Mixtral 8x22B
Mixtral 8x22B has enough public results to be ranked (#330); Llama 2-34B does not yet, so treat this comparison as directional.
Last verified . 2 shared benchmarks.
Meta
Mistral AISummary
- They share 2 benchmarks with published results for both.
- Mixtral 8x22B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-34B | Mixtral 8x22B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | — | 26.7 |
| Released | 2023-07-18 | 2024-04-17 |
| Weights | Proprietary | Open |
| Context window | — | 64K |
| Max output | — | 64K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 10 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 2-34B: —, Mixtral 8x22B: 23.8 (#324)
| Benchmark | Llama 2-34B | Mixtral 8x22B |
|---|---|---|
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| LMArena Coding | — | 1166 |
| BigCodeBench Complete | — | 50.2% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use Not comparable
Llama 2-34B: —, Mixtral 8x22B: 22.8 (#119)
| Benchmark | Llama 2-34B | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |
Reasoning Not comparable
Llama 2-34B: —, Mixtral 8x22B: 19.1 (#246)
| Benchmark | Llama 2-34B | Mixtral 8x22B |
|---|---|---|
| Epoch Capabilities Index | 104.81 | 122 |
| LMArena Hard Prompts | — | 1150 |
| DTBench | — | 55.1% |
| BIG-Bench Hard | 44.1% | — |
| ForecastBench | — | 56.3 |
| PIQA | 81.9% | — |
| WinoGrande | 76.7% | — |
Math Not comparable
Llama 2-34B: —, Mixtral 8x22B: 21.2 (#271)
| Benchmark | Llama 2-34B | Mixtral 8x22B |
|---|---|---|
| Omni-MATH | — | 16.3% |
| LMArena Math | — | 1184 |
| MATH Level 5 | — | 24.2% |
| GSM8K | 42.2% | — |
Knowledge Not comparable
Llama 2-34B: —, Mixtral 8x22B: 15.1 (#288)
| Benchmark | Llama 2-34B | Mixtral 8x22B |
|---|---|---|
| MMLU | 62.6% | 77.8% |
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| GPQA (HELM) | — | 33.4% |
| LMArena Expert | — | 1113 |
| ARC (AI2) Challenge | 54.5% | — |
| BoolQ | 83.7% | — |
| OpenBookQA | 58.2% | — |
| TriviaQA | 84.6% | — |
Multilingual Not comparable
Llama 2-34B: —, Mixtral 8x22B: 32.9 (#250)
| Benchmark | Llama 2-34B | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | — | 1128 |
| LMArena Chinese | — | 1116 |
| LMArena French | — | 1165 |
| LMArena German | — | 1141 |
| LMArena Japanese | — | 1037 |
| LMArena Korean | — | 1056 |
| LMArena Russian | — | 1158 |
| LMArena Spanish | — | 1150 |
Instruction Following Not comparable
Llama 2-34B: —, Mixtral 8x22B: 57.9 (#261)
| Benchmark | Llama 2-34B | Mixtral 8x22B |
|---|---|---|
| IFEval | — | 72.4% |
| LMArena Instruction Following | — | 1147 |
Long Context Not comparable
Llama 2-34B: —, Mixtral 8x22B: 34.6 (#242)
| Benchmark | Llama 2-34B | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | — | 1144 |
Writing & Preference Not comparable
Llama 2-34B: —, Mixtral 8x22B: 37.1 (#257)
| Benchmark | Llama 2-34B | Mixtral 8x22B |
|---|---|---|
| LMArena Text | — | 1162 |
| LMArena Creative Writing | — | 1141 |
| WildBench | — | 71.1% |
| LMArena Multi-Turn | — | 1130 |
Frequently asked questions
Is Llama 2-34B better than Mixtral 8x22B?
Mixtral 8x22B has enough public results to be ranked (#330); Llama 2-34B does not yet, so treat this comparison as directional.
How many benchmarks do Llama 2-34B and Mixtral 8x22B share?
2 benchmarks have published results for both models. Llama 2-34B has 10 scored results on Noometry and Mixtral 8x22B has 34.