Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Mixtral 8x22B
Mixtral 8x22B has enough public results to be ranked (#333); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 4 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 4 benchmarks with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and Mixtral 8x22B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 40.4 to 24.2.
- The biggest single-benchmark swing is BigCodeBench Complete: 59.4% for DeepSeek-V2 (MoE-236B, May 2024) and 50.2% for Mixtral 8x22B.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Mixtral 8x22B | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 40.3 | 27.1 |
| Released | 2024-05-07 | 2024-04-17 |
| Weights | Open | 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 DeepSeek-V2 (MoE-236B, May 2024) leads
DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139), Mixtral 8x22B: 24.2 (#329)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mixtral 8x22B |
|---|---|---|
| BigCodeBench Instruct | 48.9% | 40.6% |
| BigCodeBench Complete | 59.4% | 50.2% |
| WeirdML | — | 3.2% |
| LMArena Coding | — | 1166 |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Mixtral 8x22B: 23.1 (#127)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Mixtral 8x22B: 19.9 (#248)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mixtral 8x22B |
|---|---|---|
| Epoch Capabilities Index | 124.77 | 122.03 |
| LMArena Hard Prompts | — | 1150 |
| DTBench | — | 55.1% |
| BIG-Bench Hard | 78.8% | — |
| ForecastBench | — | 56.3 |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Mixtral 8x22B: 22.9 (#275)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mixtral 8x22B |
|---|---|---|
| Omni-MATH | — | 16.3% |
| LMArena Math | — | 1184 |
| MATH Level 5 | — | 24.2% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Mixtral 8x22B: 15.1 (#293)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mixtral 8x22B |
|---|---|---|
| MMLU | 78.4% | 77.8% |
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| GPQA (HELM) | — | 33.4% |
| LMArena Expert | — | 1113 |
| ARC (AI2) Challenge | 92.2% | — |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Mixtral 8x22B: 32.8 (#255)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | — | 1128 |
| LMArena Chinese | — | 1116 |
| LMArena French | — | 1166 |
| LMArena German | — | 1141 |
| LMArena Japanese | — | 1037 |
| LMArena Korean | — | 1057 |
| LMArena Russian | — | 1158 |
| LMArena Spanish | — | 1151 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Mixtral 8x22B: 57.7 (#266)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mixtral 8x22B |
|---|---|---|
| IFEval | — | 72.4% |
| LMArena Instruction Following | — | 1147 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Mixtral 8x22B: 34.7 (#247)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | — | 1144 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Mixtral 8x22B: 36.9 (#262)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Mixtral 8x22B |
|---|---|---|
| LMArena Text | — | 1162 |
| LMArena Creative Writing | — | 1141 |
| WildBench | — | 71.1% |
| LMArena Multi-Turn | — | 1130 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Mixtral 8x22B?
Mixtral 8x22B has enough public results to be ranked (#333); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Mixtral 8x22B better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 24.2 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Mixtral 8x22B share?
4 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Mixtral 8x22B has 34.