# DeepSeek-V3.1 vs Grok-2 (Dec 2024)

> DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-vs-grok-2
- Last updated: 2026-10-11
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and Grok-2 (Dec 2024) in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1 leads 38.9 to 20.8.
- The biggest single-benchmark swing is DTBench: 82.7% for DeepSeek-V3.1 and 65.2% for Grok-2 (Dec 2024).
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V3.1 | Grok-2 (Dec 2024) |
|---|---|---|
| Provider | DeepSeek | xAI |
| Noometry Index | 42.8 | 33.7 |
| Rank | 108 | 239 |
| Context | 164K | — |
| Input $/M | $0.25 | — |
| Output $/M | $0.95 | — |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V3.1: 40.3 (#144)
- Grok-2 (Dec 2024): 33.3 (#258)

| Benchmark | DeepSeek-V3.1 | Grok-2 (Dec 2024) |
|---|---|---|
| WeirdML | 38.4% | 22.2% |
| LMArena Coding | 1417 | 1287 |
| LiveBench Coding | — | 46.4% |

## Reasoning

- DeepSeek-V3.1: 27.9 (#110)
- Grok-2 (Dec 2024): 16.9 (#299)

| Benchmark | DeepSeek-V3.1 | Grok-2 (Dec 2024) |
|---|---|---|
| SimpleBench | 40% | 22.7% |
| LMArena Hard Prompts | 1417 | 1272 |
| DTBench | 82.7% | 65.2% |
| Epoch Capabilities Index | 139.92 | 130.48 |
| Kagi LLM Benchmark | 53.2% | — |
| LiveBench Reasoning | — | 54.8% |
| LiveBench Data Analysis | — | 54.5% |
| LMCA | 24.3% | — |
| ForecastBench | 58 | — |
| LiveBench | — | 54.3% |

## Math

- DeepSeek-V3.1: 38.9 (#122)
- Grok-2 (Dec 2024): 20.8 (#284)

| Benchmark | DeepSeek-V3.1 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Math | 1420 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 11.5% |
| LiveBench Math | — | 54.9% |
| MATH Level 5 | — | 63.5% |
| FrontierMath (Feb 2025 set) | — | 0.7% |

## Knowledge

- DeepSeek-V3.1: 43.7 (#90)
- Grok-2 (Dec 2024): 29.8 (#233)

| Benchmark | DeepSeek-V3.1 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Expert | 1405 | 1254 |
| GPQA Diamond | — | 53.8% |
| Confabulations | — | 20.1% |
| Vectara Hallucination Rate | 5.5% | — |

## Multilingual

- DeepSeek-V3.1: 51.6 (#106)
- Grok-2 (Dec 2024): 43.1 (#188)

| Benchmark | DeepSeek-V3.1 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1400 | 1282 |
| LMArena Chinese | 1469 | 1289 |
| LMArena French | 1447 | 1318 |
| LMArena German | 1411 | 1287 |
| LMArena Japanese | 1378 | 1244 |
| LMArena Korean | 1337 | 1237 |
| LMArena Russian | 1405 | 1286 |
| LMArena Spanish | 1431 | 1281 |

## Instruction Following

- DeepSeek-V3.1: 73.9 (#110)
- Grok-2 (Dec 2024): 66.9 (#202)

| Benchmark | DeepSeek-V3.1 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Instruction Following | 1400 | 1270 |
| LiveBench Instruction Following | — | 69.6% |

## Long Context

- DeepSeek-V3.1: 36.3 (#232)
- Grok-2 (Dec 2024): 38.8 (#190)

| Benchmark | DeepSeek-V3.1 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1422 | 1276 |
| Fiction.LiveBench | 52.8% | — |

## Writing & Preference

- DeepSeek-V3.1: 60.3 (#98)
- Grok-2 (Dec 2024): 48.6 (#198)

| Benchmark | DeepSeek-V3.1 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1420 | 1305 |
| LMArena Creative Writing | 1401 | 1284 |
| LMArena Multi-Turn | 1408 | 1290 |
| Short-Story Creative Writing | — | 63.6% |
| EQ-Bench Creative Writing | 1436 | — |
| LiveBench Language | — | 45.6% |

## FAQ

### Is DeepSeek-V3.1 better than Grok-2 (Dec 2024)?

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 33.7 on the Noometry Index.

### Is DeepSeek-V3.1 or Grok-2 (Dec 2024) better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 33.3 in the Noometry coding category.

### How many benchmarks do DeepSeek-V3.1 and Grok-2 (Dec 2024) share?

21 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Grok-2 (Dec 2024) has 34.