Model comparison
Deepseek Coder v2 vs Grok 2 Mini 2024 08 13
Grok 2 Mini 2024 08 13 is the stronger model overall, scoring 37.7 to 35.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 1 category and Grok 2 Mini 2024 08 13 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok 2 Mini 2024 08 13 leads 47.3 to 38.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Grok 2 Mini 2024 08 13 | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 35.9 | 37.7 |
| Released | 2024-06-17 | 2024-08-13 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
Deepseek Coder v2: 38.1 (#183), Grok 2 Mini 2024 08 13: 37.0 (#199)
| Benchmark | Deepseek Coder v2 | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Coding | 1251 | 1269 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Grok 2 Mini 2024 08 13 leads
Deepseek Coder v2: 23.6 (#176), Grok 2 Mini 2024 08 13: 24.8 (#159)
| Benchmark | Deepseek Coder v2 | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1255 |
| WinoGrande | 83.7% | — |
Math Too close to call
Deepseek Coder v2: 34.9 (#190), Grok 2 Mini 2024 08 13: 35.4 (#185)
| Benchmark | Deepseek Coder v2 | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Math | 1241 | 1265 |
| GSM8K | 94.5% | — |
Knowledge Grok 2 Mini 2024 08 13 leads
Deepseek Coder v2: 32.3 (#212), Grok 2 Mini 2024 08 13: 33.9 (#200)
| Benchmark | Deepseek Coder v2 | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Expert | 1181 | 1238 |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Grok 2 Mini 2024 08 13 leads
Deepseek Coder v2: 36.3 (#240), Grok 2 Mini 2024 08 13: 41.4 (#208)
| Benchmark | Deepseek Coder v2 | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Non-English | 1182 | 1257 |
| LMArena Chinese | 1201 | 1262 |
| LMArena French | 1185 | 1286 |
| LMArena German | 1164 | 1273 |
| LMArena Japanese | 1126 | 1213 |
| LMArena Korean | 1104 | 1195 |
| LMArena Russian | 1188 | 1261 |
| LMArena Spanish | 1153 | 1279 |
Instruction Following Grok 2 Mini 2024 08 13 leads
Deepseek Coder v2: 61.7 (#242), Grok 2 Mini 2024 08 13: 65.5 (#220)
| Benchmark | Deepseek Coder v2 | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Instruction Following | 1180 | 1245 |
Long Context Grok 2 Mini 2024 08 13 leads
Deepseek Coder v2: 37.0 (#224), Grok 2 Mini 2024 08 13: 38.4 (#196)
| Benchmark | Deepseek Coder v2 | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Longer Query | 1219 | 1266 |
Writing & Preference Grok 2 Mini 2024 08 13 leads
Deepseek Coder v2: 38.2 (#253), Grok 2 Mini 2024 08 13: 47.3 (#211)
| Benchmark | Deepseek Coder v2 | Grok 2 Mini 2024 08 13 |
|---|---|---|
| LMArena Text | 1191 | 1281 |
| LMArena Creative Writing | 1120 | 1242 |
| LMArena Multi-Turn | 1177 | 1265 |
Frequently asked questions
Is Deepseek Coder v2 better than Grok 2 Mini 2024 08 13?
Grok 2 Mini 2024 08 13 is the stronger model overall, scoring 37.7 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Grok 2 Mini 2024 08 13 better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 37.0 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Grok 2 Mini 2024 08 13 share?
17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Grok 2 Mini 2024 08 13 has 17.