Model comparison
DeepSeek Coder 6.7B vs Grok 4
Grok 4 has enough public results to be ranked (#56); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
DeepSeekSummary
- They share 1 benchmark with published results for both. DeepSeek Coder 6.7B scores higher in 0 categories and Grok 4 in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where Grok 4 leads 50.3 to 35.8.
- DeepSeek Coder 6.7B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek Coder 6.7B | Grok 4 | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 37.6 | 48.1 |
| Released | 2023-11-02 | 2025-07-09 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4 leads
DeepSeek Coder 6.7B: 35.8 (#219), Grok 4: 50.3 (#46)
| Benchmark | DeepSeek Coder 6.7B | Grok 4 |
|---|---|---|
| Aider Polyglot | — | 79.6% |
| WeirdML | — | 45.7% |
| BigCodeBench Instruct | 35.5% | — |
| LMArena Coding | — | 1408 |
| BigCodeBench Complete | 43.8% | — |
| HumanEval+ | 71.3% | — |
| MBPP+ | 65.6% | — |
Agentic & Tool Use Not comparable
DeepSeek Coder 6.7B: —, Grok 4: 32.3 (#68)
| Benchmark | DeepSeek Coder 6.7B | Grok 4 |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| Cybench | — | 43% |
| DeepResearch Bench | — | 47.3% |
| BALROG | — | 43.6% |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 66.6% |
Reasoning Not comparable
DeepSeek Coder 6.7B: —, Grok 4: 36.7 (#65)
| Benchmark | DeepSeek Coder 6.7B | Grok 4 |
|---|---|---|
| Epoch Capabilities Index | 89.62 | 146.44 |
| ARC-AGI-2 | — | 16% |
| SimpleBench | — | 60.5% |
| Kagi LLM Benchmark | — | 73.6% |
| ARC-AGI-1 | — | 66.7% |
| Chess Puzzles | — | 28% |
| LMArena Hard Prompts | — | 1409 |
| ForecastBench | — | 60.9 |
| WinoGrande | 57.6% | — |
Math Not comparable
DeepSeek Coder 6.7B: —, Grok 4: 48.4 (#64)
| Benchmark | DeepSeek Coder 6.7B | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 84% |
| Omni-MATH | — | 60.3% |
| LMArena Math | — | 1422 |
| FrontierMath (Feb 2025 set) | — | 19.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
| GSM8K | 21.3% | — |
Knowledge Not comparable
DeepSeek Coder 6.7B: —, Grok 4: 53.8 (#55)
| Benchmark | DeepSeek Coder 6.7B | Grok 4 |
|---|---|---|
| GPQA Diamond | — | 87% |
| MMLU-Pro | — | 85.1% |
| Confabulations | — | 12.4% |
| GPQA (HELM) | — | 72.7% |
| LMArena Expert | — | 1415 |
| ARC (AI2) Challenge | 36.4% | — |
| MMLU | 36.4% | — |
Multimodal Not comparable
DeepSeek Coder 6.7B: —, Grok 4: 33.7 (#94)
| Benchmark | DeepSeek Coder 6.7B | Grok 4 |
|---|---|---|
| LMArena Vision | — | 1210 |
| GeoBench | — | 45% |
Multilingual Not comparable
DeepSeek Coder 6.7B: —, Grok 4: 51.8 (#103)
| Benchmark | DeepSeek Coder 6.7B | Grok 4 |
|---|---|---|
| LMArena Non-English | — | 1403 |
| LMArena Chinese | — | 1427 |
| LMArena French | — | 1418 |
| LMArena German | — | 1429 |
| LMArena Japanese | — | 1394 |
| LMArena Korean | — | 1377 |
| LMArena Russian | — | 1410 |
| LMArena Spanish | — | 1420 |
Instruction Following Not comparable
DeepSeek Coder 6.7B: —, Grok 4: 79.2 (#5)
| Benchmark | DeepSeek Coder 6.7B | Grok 4 |
|---|---|---|
| IFEval | — | 94.9% |
| LMArena Instruction Following | — | 1387 |
Long Context Not comparable
DeepSeek Coder 6.7B: —, Grok 4: 63.1 (#4)
| Benchmark | DeepSeek Coder 6.7B | Grok 4 |
|---|---|---|
| Fiction.LiveBench | — | 94.4% |
| LMArena Longer Query | — | 1409 |
Writing & Preference Not comparable
DeepSeek Coder 6.7B: —, Grok 4: 58.5 (#116)
| Benchmark | DeepSeek Coder 6.7B | Grok 4 |
|---|---|---|
| LMArena Text | — | 1411 |
| LMArena Creative Writing | — | 1397 |
| Short-Story Creative Writing | — | 76.9% |
| WildBench | — | 79.7% |
| LMArena Multi-Turn | — | 1416 |
Frequently asked questions
Is DeepSeek Coder 6.7B better than Grok 4?
Grok 4 has enough public results to be ranked (#56); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 6.7B or Grok 4 better for coding?
Grok 4 scores higher on coding benchmarks: 50.3 versus 35.8 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 6.7B and Grok 4 share?
1 benchmark has published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Grok 4 has 48.