Model comparison
DeepSeek LLM 67B vs Grok 4.1
Grok 4.1 is the stronger model overall, scoring 41.5 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeekSummary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Grok 4.1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 4.1 leads 39.5 to 7.0.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Grok 4.1 | |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 24.9 | 41.5 |
| Released | 2023-11-29 | 2025-11-17 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.1 leads
DeepSeek LLM 67B: 31.9 (#278), Grok 4.1: 33.7 (#253)
| Benchmark | DeepSeek LLM 67B | Grok 4.1 |
|---|---|---|
| LMArena Coding | 1096 | 1445 |
| LMArena WebDev | — | 1214 |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, Grok 4.1: 34.1 (#49)
| Benchmark | DeepSeek LLM 67B | Grok 4.1 |
|---|---|---|
| Cybench | — | 39% |
Reasoning Grok 4.1 leads
DeepSeek LLM 67B: 16.5 (#304), Grok 4.1: 29.5 (#91)
| Benchmark | DeepSeek LLM 67B | Grok 4.1 |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1435 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math Grok 4.1 leads
DeepSeek LLM 67B: 8.7 (#324), Grok 4.1: 38.9 (#120)
| Benchmark | DeepSeek LLM 67B | Grok 4.1 |
|---|---|---|
| LMArena Math | 1108 | 1422 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge Grok 4.1 leads
DeepSeek LLM 67B: 7.0 (#313), Grok 4.1: 39.5 (#133)
| Benchmark | DeepSeek LLM 67B | Grok 4.1 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1417 |
Multilingual Grok 4.1 leads
DeepSeek LLM 67B: 29.4 (#267), Grok 4.1: 53.4 (#68)
| Benchmark | DeepSeek LLM 67B | Grok 4.1 |
|---|---|---|
| LMArena Non-English | 1073 | 1425 |
| LMArena Chinese | 1132 | 1465 |
| LMArena French | — | 1448 |
| LMArena German | — | 1446 |
| LMArena Japanese | — | 1397 |
| LMArena Korean | — | 1407 |
| LMArena Russian | — | 1434 |
| LMArena Spanish | — | 1438 |
Instruction Following Grok 4.1 leads
DeepSeek LLM 67B: 55.4 (#277), Grok 4.1: 73.8 (#111)
| Benchmark | DeepSeek LLM 67B | Grok 4.1 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1400 |
Long Context Grok 4.1 leads
DeepSeek LLM 67B: 33.1 (#265), Grok 4.1: 43.2 (#100)
| Benchmark | DeepSeek LLM 67B | Grok 4.1 |
|---|---|---|
| LMArena Longer Query | 1092 | 1416 |
Writing & Preference Grok 4.1 leads
DeepSeek LLM 67B: 31.6 (#282), Grok 4.1: 62.4 (#75)
| Benchmark | DeepSeek LLM 67B | Grok 4.1 |
|---|---|---|
| LMArena Text | 1105 | 1437 |
| LMArena Creative Writing | 1067 | 1411 |
| LMArena Multi-Turn | 1082 | 1437 |
Frequently asked questions
Is DeepSeek LLM 67B better than Grok 4.1?
Grok 4.1 is the stronger model overall, scoring 41.5 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Grok 4.1 better for coding?
Grok 4.1 scores higher on coding benchmarks: 33.7 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Grok 4.1 share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Grok 4.1 has 19.