# DeepSeek V4 Pro vs Grok 4.20 (Non-Reasoning)

> DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 48.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-pro-vs-grok-4-20
- Last updated: 2026-10-10
- Shared benchmarks: 38

## Summary

- They share 38 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 5 categories and Grok 4.20 (Non-Reasoning) in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4 Pro leads 64.6 to 48.0.
- The biggest single-benchmark swing is ProofBench: 50% for DeepSeek V4 Pro and 14% for Grok 4.20 (Non-Reasoning).
- DeepSeek V4 Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek V4 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 54.2 | 48.5 |
| Rank | 28 | 48 |
| Context | 1M | 1M |
| Input $/M | $0.43 | $1.25 |
| Output $/M | $0.87 | $2.50 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek V4 Pro: 52.2 (#31)
- Grok 4.20 (Non-Reasoning): 41.8 (#104)

| Benchmark | DeepSeek V4 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena WebDev | 1582 | 1374 |
| WeirdML | 66.2% | 52.3% |
| LMArena Coding | 1470 | 1458 |
| ALE-Bench | 1,403 | 1,150 |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| SciCode | 51% | — |

## Agentic & Tool Use

- DeepSeek V4 Pro: 32.7 (#54)
- Grok 4.20 (Non-Reasoning): 34.3 (#43)

| Benchmark | DeepSeek V4 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Vending-Bench 2 | 3,285 | 4,663 |
| Terminal-Bench | — | 57.3% |
| APEX-Agents | 47.3% | — |
| τ²-bench Banking | — | 18% |
| LMArena Search | — | 1189 |

## Reasoning

- DeepSeek V4 Pro: 56.4 (#22)
- Grok 4.20 (Non-Reasoning): 52.2 (#30)

| Benchmark | DeepSeek V4 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| ARC-AGI-2 | 61.3% | 65.1% |
| Kagi LLM Benchmark | 53.5% | 75% |
| NYT Connections (extended) | 91.3% | 85.4% |
| ARC-AGI-1 | 90.5% | 89.5% |
| Chess Puzzles | 47% | 24% |
| LMArena Hard Prompts | 1461 | 1451 |
| DTBench | 93.9% | 90.1% |
| LMCA | 45.5% | 38.7% |
| Epoch Capabilities Index | 155.39 | 152.01 |
| ForecastBench | 56.1 | 61.4 |
| CritPt | 18% | — |
| Thematic Generalization | — | 63.8% |
| Mystery Game Puzzles | 43% | — |
| Surface Evolver Bench | 40% | — |

## Math

- DeepSeek V4 Pro: 64.6 (#24)
- Grok 4.20 (Non-Reasoning): 48.0 (#54)

| Benchmark | DeepSeek V4 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| FrontierMath (Tiers 1-3) | 64.6% | 44.9% |
| FrontierMath Tier 4 | 26.8% | 17.1% |
| OTIS Mock AIME 2024-2025 | 98.6% | 92.2% |
| ProofBench | 50% | 14% |
| LMArena Math | 1455 | 1455 |
| MathArena Final-Answer Competitions | 76.6% | — |

## Knowledge

- DeepSeek V4 Pro: 59.5 (#28)
- Grok 4.20 (Non-Reasoning): 52.8 (#54)

| Benchmark | DeepSeek V4 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 91.7% | 89.3% |
| SimpleQA Verified | 52.9% | 30.2% |
| LMArena Expert | 1463 | 1440 |
| Vectara Hallucination Rate | 8.6% | — |

## Multimodal

- DeepSeek V4 Pro: —
- Grok 4.20 (Non-Reasoning): 33.2 (#88)

| Benchmark | DeepSeek V4 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | — | 1263 |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |

## Multilingual

- DeepSeek V4 Pro: 54.5 (#44)
- Grok 4.20 (Non-Reasoning): 54.7 (#38)

| Benchmark | DeepSeek V4 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1438 | 1440 |
| LMArena Chinese | 1486 | 1481 |
| LMArena French | 1473 | 1477 |
| LMArena German | 1458 | 1463 |
| LMArena Japanese | 1448 | 1450 |
| LMArena Korean | 1452 | 1417 |
| LMArena Russian | 1452 | 1457 |
| LMArena Spanish | 1457 | 1442 |

## Instruction Following

- DeepSeek V4 Pro: 76.3 (#44)
- Grok 4.20 (Non-Reasoning): 75.0 (#79)

| Benchmark | DeepSeek V4 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1448 | 1420 |

## Long Context

- DeepSeek V4 Pro: 45.0 (#49)
- Grok 4.20 (Non-Reasoning): 45.4 (#33)

| Benchmark | DeepSeek V4 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| CL-bench Life | 13.5% | 11.9% |
| LMArena Longer Query | 1459 | 1436 |
| CL-bench | — | 22.2% |

## Writing & Preference

- DeepSeek V4 Pro: 65.6 (#45)
- Grok 4.20 (Non-Reasoning): 65.9 (#42)

| Benchmark | DeepSeek V4 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1451 | 1451 |
| LMArena Creative Writing | 1446 | 1439 |
| EQ-Bench Creative Writing | 1553 | 1574 |
| LMArena Multi-Turn | 1467 | 1456 |
| EQ-Bench 4 | 1166 | — |

## FAQ

### Is DeepSeek V4 Pro better than Grok 4.20 (Non-Reasoning)?

DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 48.5 on the Noometry Index.

### Which is cheaper, DeepSeek V4 Pro or Grok 4.20 (Non-Reasoning)?

DeepSeek V4 Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

### Is DeepSeek V4 Pro or Grok 4.20 (Non-Reasoning) better for coding?

DeepSeek V4 Pro scores higher on coding benchmarks: 52.2 versus 41.8 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1M tokens.

### How many benchmarks do DeepSeek V4 Pro and Grok 4.20 (Non-Reasoning) share?

38 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.