# Grok-2 (Dec 2024) vs Qwen2-72B

> Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 30.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-2-vs-qwen2-72b
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 6 categories and Qwen2-72B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2-72B leads 30.2 to 20.8.
- The biggest single-benchmark swing is MATH Level 5: 63.5% for Grok-2 (Dec 2024) and 39.1% for Qwen2-72B.
- Qwen2-72B has downloadable open weights; the other is API-only.

## Snapshot

| | Grok-2 (Dec 2024) | Qwen2-72B |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 33.7 | 30.0 |
| Rank | 239 | 300 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Grok-2 (Dec 2024): 33.3 (#258)
- Qwen2-72B: 29.1 (#310)

| Benchmark | Grok-2 (Dec 2024) | Qwen2-72B |
|---|---|---|
| WeirdML | 22.2% | 11.3% |
| LMArena Coding | 1287 | 1196 |
| BigCodeBench Instruct | — | 38.5% |
| LiveBench Coding | 46.4% | — |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- Grok-2 (Dec 2024): —
- Qwen2-72B: 17.0 (#146)

| Benchmark | Grok-2 (Dec 2024) | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Grok-2 (Dec 2024): 16.9 (#299)
- Qwen2-72B: 23.2 (#181)

| Benchmark | Grok-2 (Dec 2024) | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1272 | 1191 |
| Epoch Capabilities Index | 130.48 | 125.28 |
| SimpleBench | 22.7% | — |
| LiveBench Reasoning | 54.8% | — |
| DTBench | 65.2% | — |
| LiveBench Data Analysis | 54.5% | — |
| LiveBench | 54.3% | — |

## Math

- Grok-2 (Dec 2024): 20.8 (#284)
- Qwen2-72B: 30.2 (#236)

| Benchmark | Grok-2 (Dec 2024) | Qwen2-72B |
|---|---|---|
| LMArena Math | 1283 | 1235 |
| MATH Level 5 | 63.5% | 39.1% |
| OTIS Mock AIME 2024-2025 | 11.5% | — |
| LiveBench Math | 54.9% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |

## Knowledge

- Grok-2 (Dec 2024): 29.8 (#233)
- Qwen2-72B: 21.2 (#275)

| Benchmark | Grok-2 (Dec 2024) | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 53.8% | 40.8% |
| LMArena Expert | 1254 | 1171 |
| Confabulations | 20.1% | — |
| MMLU | — | 82.4% |

## Multilingual

- Grok-2 (Dec 2024): 43.1 (#188)
- Qwen2-72B: 35.9 (#244)

| Benchmark | Grok-2 (Dec 2024) | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1282 | 1176 |
| LMArena Chinese | 1289 | 1240 |
| LMArena French | 1318 | 1170 |
| LMArena German | 1287 | 1151 |
| LMArena Japanese | 1244 | 1111 |
| LMArena Korean | 1237 | 1083 |
| LMArena Russian | 1286 | 1169 |
| LMArena Spanish | 1281 | 1169 |

## Instruction Following

- Grok-2 (Dec 2024): 66.9 (#202)
- Qwen2-72B: 61.7 (#241)

| Benchmark | Grok-2 (Dec 2024) | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1270 | 1181 |
| LiveBench Instruction Following | 69.6% | — |

## Long Context

- Grok-2 (Dec 2024): 38.8 (#190)
- Qwen2-72B: 36.1 (#235)

| Benchmark | Grok-2 (Dec 2024) | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1276 | 1192 |

## Writing & Preference

- Grok-2 (Dec 2024): 48.6 (#198)
- Qwen2-72B: 40.8 (#241)

| Benchmark | Grok-2 (Dec 2024) | Qwen2-72B |
|---|---|---|
| LMArena Text | 1305 | 1203 |
| LMArena Creative Writing | 1284 | 1181 |
| LMArena Multi-Turn | 1290 | 1196 |
| Short-Story Creative Writing | 63.6% | — |
| LiveBench Language | 45.6% | — |

## FAQ

### Is Grok-2 (Dec 2024) better than Qwen2-72B?

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 30.0 on the Noometry Index.

### Is Grok-2 (Dec 2024) or Qwen2-72B better for coding?

Grok-2 (Dec 2024) scores higher on coding benchmarks: 33.3 versus 29.1 in the Noometry coding category.

### How many benchmarks do Grok-2 (Dec 2024) and Qwen2-72B share?

21 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Qwen2-72B has 26.