Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Ministral 8B
Ministral 8B has enough public results to be ranked (#321); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
DeepSeek
Mistral AISummary
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 39.8 to 34.4.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Ministral 8B | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 39.7 | 27.8 |
| Released | 2024-05-07 | 2024-10-01 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.10 |
| Results tracked | 10 | 17 |
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): 39.8 (#141), Ministral 8B: 34.4 (#226)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Ministral 8B |
|---|---|---|
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1202 |
| BigCodeBench Complete | 59.4% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Ministral 8B: 16.2 (#140)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Ministral 8B: 17.7 (#279)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | — | 1191 |
| DTBench | — | 45.7% |
| BIG-Bench Hard | 78.8% | — |
| Epoch Capabilities Index | 124.78 | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Ministral 8B: 23.7 (#262)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Ministral 8B |
|---|---|---|
| LMArena Math | — | 1188 |
| MATH Level 5 | — | 14.9% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Ministral 8B: 12.5 (#292)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Ministral 8B |
|---|---|---|
| GPQA Diamond | — | 27.1% |
| Vectara Hallucination Rate | — | 7.4% |
| LMArena Expert | — | 1170 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Ministral 8B: 35.3 (#242)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Ministral 8B |
|---|---|---|
| LMArena Non-English | — | 1165 |
| LMArena Chinese | — | 1193 |
| LMArena Russian | — | 1195 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Ministral 8B: 60.7 (#245)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | — | 1161 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Ministral 8B: 36.7 (#222)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Ministral 8B |
|---|---|---|
| LMArena Longer Query | — | 1212 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Ministral 8B: 39.8 (#241)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Ministral 8B |
|---|---|---|
| LMArena Text | — | 1191 |
| LMArena Creative Writing | — | 1175 |
| LMArena Multi-Turn | — | 1166 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Ministral 8B?
Ministral 8B has enough public results to be ranked (#321); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Ministral 8B better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 39.8 versus 34.4 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Ministral 8B share?
0 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Ministral 8B has 17.