Model comparison
Deepseek Coder v2 vs Mistral Nemo
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 26.4 on the Noometry Index.
Last verified . 1 shared benchmarks.
DeepSeek
Mistral AISummary
- They share 1 benchmark with published results for both. Deepseek Coder v2 scores higher in 4 categories and Mistral Nemo in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Deepseek Coder v2 leads 32.3 to 12.3.
Side by side
| Deepseek Coder v2 | Mistral Nemo | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 35.9 | 26.4 |
| Released | 2024-06-17 | 2024-07-01 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 24 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Deepseek Coder v2: 38.1 (#183), Mistral Nemo: —
| Benchmark | Deepseek Coder v2 | Mistral Nemo |
|---|---|---|
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1251 | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Agentic & Tool Use Not comparable
Deepseek Coder v2: —, Mistral Nemo: 23.5 (#125)
| Benchmark | Deepseek Coder v2 | Mistral Nemo |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 27.6% |
| BALROG | — | 17.6% |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 23.6 (#176), Mistral Nemo: 20.7 (#232)
| Benchmark | Deepseek Coder v2 | Mistral Nemo |
|---|---|---|
| LMArena Hard Prompts | 1207 | — |
| DTBench | — | 48.6% |
| Epoch Capabilities Index | — | 118.68 |
| PIQA | — | 83.5% |
| WinoGrande | 83.7% | — |
Math Deepseek Coder v2 leads
Deepseek Coder v2: 34.9 (#190), Mistral Nemo: 25.5 (#268)
| Benchmark | Deepseek Coder v2 | Mistral Nemo |
|---|---|---|
| GSM8K | 94.5% | 84.2% |
| LMArena Math | 1241 | — |
| MATH Level 5 | — | 10.8% |
Knowledge Deepseek Coder v2 leads
Deepseek Coder v2: 32.3 (#212), Mistral Nemo: 12.3 (#298)
| Benchmark | Deepseek Coder v2 | Mistral Nemo |
|---|---|---|
| GPQA Diamond | — | 29.9% |
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |
| BoolQ | — | 82.5% |
Multilingual Not comparable
Deepseek Coder v2: 36.3 (#240), Mistral Nemo: —
| Benchmark | Deepseek Coder v2 | Mistral Nemo |
|---|---|---|
| LMArena Non-English | 1182 | — |
| LMArena Chinese | 1201 | — |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Russian | 1188 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Not comparable
Deepseek Coder v2: 61.7 (#242), Mistral Nemo: —
| Benchmark | Deepseek Coder v2 | Mistral Nemo |
|---|---|---|
| LMArena Instruction Following | 1180 | — |
Long Context Not comparable
Deepseek Coder v2: 37.0 (#224), Mistral Nemo: —
| Benchmark | Deepseek Coder v2 | Mistral Nemo |
|---|---|---|
| LMArena Longer Query | 1219 | — |
Writing & Preference Deepseek Coder v2 leads
Deepseek Coder v2: 38.2 (#253), Mistral Nemo: 28.5 (#296)
| Benchmark | Deepseek Coder v2 | Mistral Nemo |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1120 | — |
| EQ-Bench Creative Writing | — | 881 |
| LMArena Multi-Turn | 1177 | — |
Frequently asked questions
Is Deepseek Coder v2 better than Mistral Nemo?
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 26.4 on the Noometry Index.
How many benchmarks do Deepseek Coder v2 and Mistral Nemo share?
1 benchmark has published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Mistral Nemo has 10.