Model comparison
Deepseek Coder v2 vs Grok Build 0.1
Deepseek Coder v2 and Grok Build 0.1 score almost the same on the Noometry Index (35.9 vs 36.4), so choose on price, context window or the category you care about most.
Last verified . 0 shared benchmarks.
DeepSeekSummary
- The widest gap is in reasoning, where Grok Build 0.1 leads 32.2 to 23.6.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Grok Build 0.1 | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 35.9 | 36.4 |
| Released | 2024-06-17 | 2026-04-16 |
| Weights | Open | Proprietary |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2 |
| Results tracked | 24 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok Build 0.1 leads
Deepseek Coder v2: 38.1 (#183), Grok Build 0.1: 43.1 (#91)
| Benchmark | Deepseek Coder v2 | Grok Build 0.1 |
|---|---|---|
| SciCode | — | 50.2% |
| 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: —, Grok Build 0.1: 22.7 (#129)
| Benchmark | Deepseek Coder v2 | Grok Build 0.1 |
|---|---|---|
| GBAEval | — | 2.4% |
Reasoning Grok Build 0.1 leads
Deepseek Coder v2: 23.6 (#176), Grok Build 0.1: 32.2 (#77)
| Benchmark | Deepseek Coder v2 | Grok Build 0.1 |
|---|---|---|
| CritPt | — | 9.1% |
| LMArena Hard Prompts | 1207 | — |
| WinoGrande | 83.7% | — |
Math Not comparable
Deepseek Coder v2: 34.9 (#190), Grok Build 0.1: —
| Benchmark | Deepseek Coder v2 | Grok Build 0.1 |
|---|---|---|
| LMArena Math | 1241 | — |
| GSM8K | 94.5% | — |
Knowledge Not comparable
Deepseek Coder v2: 32.3 (#212), Grok Build 0.1: —
| Benchmark | Deepseek Coder v2 | Grok Build 0.1 |
|---|---|---|
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Not comparable
Deepseek Coder v2: 36.3 (#240), Grok Build 0.1: —
| Benchmark | Deepseek Coder v2 | Grok Build 0.1 |
|---|---|---|
| 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), Grok Build 0.1: —
| Benchmark | Deepseek Coder v2 | Grok Build 0.1 |
|---|---|---|
| LMArena Instruction Following | 1180 | — |
Long Context Not comparable
Deepseek Coder v2: 37.0 (#224), Grok Build 0.1: —
| Benchmark | Deepseek Coder v2 | Grok Build 0.1 |
|---|---|---|
| LMArena Longer Query | 1219 | — |
Writing & Preference Not comparable
Deepseek Coder v2: 38.2 (#253), Grok Build 0.1: —
| Benchmark | Deepseek Coder v2 | Grok Build 0.1 |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1120 | — |
| LMArena Multi-Turn | 1177 | — |
Frequently asked questions
Is Deepseek Coder v2 better than Grok Build 0.1?
Deepseek Coder v2 and Grok Build 0.1 score almost the same on the Noometry Index (35.9 vs 36.4), so choose on price, context window or the category you care about most.
Is Deepseek Coder v2 or Grok Build 0.1 better for coding?
Grok Build 0.1 scores higher on coding benchmarks: 43.1 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Grok Build 0.1 share?
0 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Grok Build 0.1 has 3.