Model comparison
Deepseek Coder v2 vs Grok 4.6
Grok 4.6 is the stronger model overall, scoring 56.9 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 0 categories and Grok 4.6 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.4 to 23.6.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Grok 4.6 | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 35.9 | 56.9 |
| Released | 2024-06-17 | 2026-08-12 |
| Weights | Open | Proprietary |
| Context window | — | 500K |
| Max output | — | 500K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 24 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
Deepseek Coder v2: 38.1 (#183), Grok 4.6: 58.5 (#16)
| Benchmark | Deepseek Coder v2 | Grok 4.6 |
|---|---|---|
| LMArena Coding | 1251 | 1465 |
| DeepSWE | — | 67.5% |
| FrontierCode | — | 48% |
| CursorBench | — | 41.4% |
| LMArena WebDev | — | 1617 |
| FrontierSWE | — | 25.3% |
| SciCode | — | 56.5% |
| WeirdML | — | 67.3% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| ALE-Bench | — | 1,508 |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Agentic & Tool Use Not comparable
Deepseek Coder v2: —, Grok 4.6: 39.4 (#27)
| Benchmark | Deepseek Coder v2 | Grok 4.6 |
|---|---|---|
| APEX-Agents | — | 65.3% |
| GDP.pdf | — | 17.2% |
| Vending-Bench 2 | — | 9,047 |
Reasoning Grok 4.6 leads
Deepseek Coder v2: 23.6 (#176), Grok 4.6: 61.4 (#20)
| Benchmark | Deepseek Coder v2 | Grok 4.6 |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1447 |
| ARC-AGI-2 | — | 67.1% |
| SimpleBench | — | 75.9% |
| NYT Connections (extended) | — | 80% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 19.7% |
| Chess Puzzles | — | 40% |
| EBR-Bench | — | 30.5% |
| Mystery Game Puzzles | — | 34% |
| DTBench | — | 97.3% |
| LMCA | — | 48.5% |
| Epoch Capabilities Index | — | 156.44 |
| WinoGrande | 83.7% | — |
Math Grok 4.6 leads
Deepseek Coder v2: 34.9 (#190), Grok 4.6: 67.0 (#24)
| Benchmark | Deepseek Coder v2 | Grok 4.6 |
|---|---|---|
| LMArena Math | 1241 | 1423 |
| FrontierMath (Tiers 1-3) | — | 66% |
| FrontierMath Tier 4 | — | 31.7% |
| OTIS Mock AIME 2024-2025 | — | 99.2% |
| ProofBench | — | 51% |
| GSM8K | 94.5% | — |
Knowledge Grok 4.6 leads
Deepseek Coder v2: 32.3 (#212), Grok 4.6: 63.3 (#20)
| Benchmark | Deepseek Coder v2 | Grok 4.6 |
|---|---|---|
| LMArena Expert | 1181 | 1467 |
| GPQA Diamond | — | 94% |
| SimpleQA Verified | — | 49.3% |
| ARC (AI2) Challenge | 64.3% | — |
Multimodal Not comparable
Deepseek Coder v2: —, Grok 4.6: 43.6 (#23)
| Benchmark | Deepseek Coder v2 | Grok 4.6 |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 33.2% |
| Furniture Assembly | — | 40% |
| LMArena Document | — | 1452 |
Multilingual Grok 4.6 leads
Deepseek Coder v2: 36.3 (#240), Grok 4.6: 53.0 (#74)
| Benchmark | Deepseek Coder v2 | Grok 4.6 |
|---|---|---|
| LMArena Non-English | 1182 | 1420 |
| LMArena Chinese | 1201 | 1480 |
| LMArena French | 1185 | 1461 |
| LMArena German | 1164 | 1431 |
| LMArena Japanese | 1126 | 1376 |
| LMArena Korean | 1104 | 1397 |
| LMArena Russian | 1188 | 1422 |
| LMArena Spanish | 1153 | 1404 |
Instruction Following Grok 4.6 leads
Deepseek Coder v2: 61.7 (#242), Grok 4.6: 75.4 (#63)
| Benchmark | Deepseek Coder v2 | Grok 4.6 |
|---|---|---|
| LMArena Instruction Following | 1180 | 1431 |
Long Context Grok 4.6 leads
Deepseek Coder v2: 37.0 (#224), Grok 4.6: 44.5 (#66)
| Benchmark | Deepseek Coder v2 | Grok 4.6 |
|---|---|---|
| LMArena Longer Query | 1219 | 1454 |
Writing & Preference Grok 4.6 leads
Deepseek Coder v2: 38.2 (#253), Grok 4.6: 62.3 (#80)
| Benchmark | Deepseek Coder v2 | Grok 4.6 |
|---|---|---|
| LMArena Text | 1191 | 1428 |
| LMArena Creative Writing | 1120 | 1428 |
| LMArena Multi-Turn | 1177 | 1425 |
Frequently asked questions
Is Deepseek Coder v2 better than Grok 4.6?
Grok 4.6 is the stronger model overall, scoring 56.9 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Grok 4.6 better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Grok 4.6 share?
17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Grok 4.6 has 49.