# DeepSeek LLM 67B vs Grok 4.7

> Grok 4.7 is the stronger model overall, scoring 46.6 to 24.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-grok-4-7
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Grok 4.7 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok 4.7 leads 70.1 to 31.8.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek LLM 67B | Grok 4.7 |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 24.8 | 46.6 |
| Rank | 341 | 56 |
| Context | — | 500K |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek LLM 67B: 31.3 (#273)
- Grok 4.7: 55.0 (#23)

| Benchmark | DeepSeek LLM 67B | Grok 4.7 |
|---|---|---|
| LMArena Coding | 1096 | 1423 |
| CursorBench | — | 46.3% |
| LMArena WebDev | — | 1636 |
| FrontierSWE | — | 29.5% |
| SciCode | — | 57.4% |

## Reasoning

- DeepSeek LLM 67B: 15.9 (#300)
- Grok 4.7: 40.1 (#49)

| Benchmark | DeepSeek LLM 67B | Grok 4.7 |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1409 |
| NYT Connections (extended) | — | 76.8% |
| CritPt | — | 17.7% |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.54 | — |

## Math

- DeepSeek LLM 67B: 8.1 (#318)
- Grok 4.7: 41.1 (#73)

| Benchmark | DeepSeek LLM 67B | Grok 4.7 |
|---|---|---|
| LMArena Math | 1108 | 1393 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| ProofBench | — | 34% |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.1 (#308)
- Grok 4.7: 38.7 (#130)

| Benchmark | DeepSeek LLM 67B | Grok 4.7 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1413 |

## Multimodal

- DeepSeek LLM 67B: —
- Grok 4.7: 28.8 (#107)

| Benchmark | DeepSeek LLM 67B | Grok 4.7 |
|---|---|---|
| Furniture Assembly | — | 20.8% |

## Multilingual

- DeepSeek LLM 67B: 29.5 (#262)
- Grok 4.7: 51.2 (#108)

| Benchmark | DeepSeek LLM 67B | Grok 4.7 |
|---|---|---|
| LMArena Non-English | 1073 | 1392 |
| LMArena Chinese | 1132 | 1476 |
| LMArena Russian | — | 1396 |

## Instruction Following

- DeepSeek LLM 67B: 55.7 (#272)
- Grok 4.7: 74.3 (#98)

| Benchmark | DeepSeek LLM 67B | Grok 4.7 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1406 |

## Long Context

- DeepSeek LLM 67B: 33.1 (#260)
- Grok 4.7: 43.2 (#97)

| Benchmark | DeepSeek LLM 67B | Grok 4.7 |
|---|---|---|
| LMArena Longer Query | 1092 | 1416 |

## Writing & Preference

- DeepSeek LLM 67B: 31.8 (#277)
- Grok 4.7: 70.1 (#23)

| Benchmark | DeepSeek LLM 67B | Grok 4.7 |
|---|---|---|
| LMArena Text | 1105 | 1397 |
| LMArena Creative Writing | 1067 | 1391 |
| LMArena Multi-Turn | 1082 | 1389 |
| EQ-Bench Creative Writing | — | 2007 |

## FAQ

### Is DeepSeek LLM 67B better than Grok 4.7?

Grok 4.7 is the stronger model overall, scoring 46.6 to 24.8 on the Noometry Index.

### Is DeepSeek LLM 67B or Grok 4.7 better for coding?

Grok 4.7 scores higher on coding benchmarks: 55.0 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and Grok 4.7 share?

10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Grok 4.7 has 21.