Model comparison
DeepSeek Coder 6.7B vs Grok 4.20 (Non-Reasoning)
Grok 4.20 (Non-Reasoning) has enough public results to be ranked (#48); 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 4.20 (Non-Reasoning) in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where Grok 4.20 (Non-Reasoning) leads 41.8 to 35.2.
- DeepSeek Coder 6.7B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek Coder 6.7B | Grok 4.20 (Non-Reasoning) | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 37.1 | 48.5 |
| Released | 2023-11-02 | 2026-02-17 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 30K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 9 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 (Non-Reasoning) leads
DeepSeek Coder 6.7B: 35.2 (#216), Grok 4.20 (Non-Reasoning): 41.8 (#104)
| Benchmark | DeepSeek Coder 6.7B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena WebDev | — | 1374 |
| WeirdML | — | 52.3% |
| BigCodeBench Instruct | 35.5% | — |
| LMArena Coding | — | 1458 |
| BigCodeBench Complete | 43.8% | — |
| ALE-Bench | — | 1,150 |
| HumanEval+ | 71.3% | — |
| MBPP+ | 65.6% | — |
Agentic & Tool Use Not comparable
DeepSeek Coder 6.7B: —, Grok 4.20 (Non-Reasoning): 34.3 (#43)
| Benchmark | DeepSeek Coder 6.7B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| τ²-bench Banking | — | 18% |
| LMArena Search | — | 1189 |
| Vending-Bench 2 | — | 4,663 |
Reasoning Not comparable
DeepSeek Coder 6.7B: —, Grok 4.20 (Non-Reasoning): 52.2 (#30)
| Benchmark | DeepSeek Coder 6.7B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Epoch Capabilities Index | 88.88 | 152.01 |
| ARC-AGI-2 | — | 65.1% |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 85.4% |
| ARC-AGI-1 | — | 89.5% |
| Chess Puzzles | — | 24% |
| Thematic Generalization | — | 63.8% |
| LMArena Hard Prompts | — | 1451 |
| DTBench | — | 90.1% |
| LMCA | — | 38.7% |
| ForecastBench | — | 61.4 |
| WinoGrande | 57.6% | — |
Math Not comparable
DeepSeek Coder 6.7B: —, Grok 4.20 (Non-Reasoning): 48.0 (#54)
| Benchmark | DeepSeek Coder 6.7B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 17.1% |
| OTIS Mock AIME 2024-2025 | — | 92.2% |
| ProofBench | — | 14% |
| LMArena Math | — | 1455 |
| GSM8K | 21.3% | — |
Knowledge Not comparable
DeepSeek Coder 6.7B: —, Grok 4.20 (Non-Reasoning): 52.8 (#54)
| Benchmark | DeepSeek Coder 6.7B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | — | 89.3% |
| SimpleQA Verified | — | 30.2% |
| LMArena Expert | — | 1440 |
| ARC (AI2) Challenge | 36.4% | — |
| MMLU | 36.4% | — |
Multimodal Not comparable
DeepSeek Coder 6.7B: —, Grok 4.20 (Non-Reasoning): 33.2 (#88)
| Benchmark | DeepSeek Coder 6.7B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |
Multilingual Not comparable
DeepSeek Coder 6.7B: —, Grok 4.20 (Non-Reasoning): 54.7 (#38)
| Benchmark | DeepSeek Coder 6.7B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | — | 1440 |
| LMArena Chinese | — | 1481 |
| LMArena French | — | 1477 |
| LMArena German | — | 1463 |
| LMArena Japanese | — | 1450 |
| LMArena Korean | — | 1417 |
| LMArena Russian | — | 1457 |
| LMArena Spanish | — | 1442 |
Instruction Following Not comparable
DeepSeek Coder 6.7B: —, Grok 4.20 (Non-Reasoning): 75.0 (#79)
| Benchmark | DeepSeek Coder 6.7B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | — | 1420 |
Long Context Not comparable
DeepSeek Coder 6.7B: —, Grok 4.20 (Non-Reasoning): 45.4 (#33)
| Benchmark | DeepSeek Coder 6.7B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |
| LMArena Longer Query | — | 1436 |
Writing & Preference Not comparable
DeepSeek Coder 6.7B: —, Grok 4.20 (Non-Reasoning): 65.9 (#42)
| Benchmark | DeepSeek Coder 6.7B | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | — | 1451 |
| LMArena Creative Writing | — | 1439 |
| EQ-Bench Creative Writing | — | 1574 |
| LMArena Multi-Turn | — | 1456 |
Frequently asked questions
Is DeepSeek Coder 6.7B better than Grok 4.20 (Non-Reasoning)?
Grok 4.20 (Non-Reasoning) has enough public results to be ranked (#48); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 6.7B or Grok 4.20 (Non-Reasoning) better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 41.8 versus 35.2 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 6.7B and Grok 4.20 (Non-Reasoning) share?
1 benchmark has published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.