# Grok 4.7 vs Qwen2.5 72B Instruct

> Grok 4.7 is the stronger model overall, scoring 46.6 to 31.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-4-7-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Grok 4.7 scores higher in 8 categories and Qwen2.5 72B Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok 4.7 leads 70.1 to 46.9.
- Qwen2.5 72B Instruct is cheaper at $1.40 / $5.60 per million input/output tokens, against $2 / $6 for Grok 4.7.
- Grok 4.7 accepts more context: 500K tokens versus 131K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 4.7 | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 46.6 | 31.5 |
| Rank | 56 | 259 |
| Context | 500K | 131K |
| Input $/M | $2 | $1.40 |
| Output $/M | $6 | $5.60 |
| Weights | Proprietary | Open |

## Coding

- Grok 4.7: 55.0 (#23)
- Qwen2.5 72B Instruct: 32.8 (#256)

| Benchmark | Grok 4.7 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1423 | 1293 |
| CursorBench | 46.3% | — |
| LMArena WebDev | 1636 | — |
| FrontierSWE | 29.5% | — |
| SciCode | 57.4% | — |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |

## Agentic & Tool Use

- Grok 4.7: —
- Qwen2.5 72B Instruct: 22.0 (#124)

| Benchmark | Grok 4.7 | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |

## Reasoning

- Grok 4.7: 40.1 (#49)
- Qwen2.5 72B Instruct: 21.4 (#197)

| Benchmark | Grok 4.7 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1409 | 1271 |
| NYT Connections (extended) | 76.8% | — |
| CritPt | 17.7% | — |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129.01 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |

## Math

- Grok 4.7: 41.1 (#73)
- Qwen2.5 72B Instruct: 18.1 (#281)

| Benchmark | Grok 4.7 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1393 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| ProofBench | 34% | — |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |

## Knowledge

- Grok 4.7: 38.7 (#130)
- Qwen2.5 72B Instruct: 26.9 (#247)

| Benchmark | Grok 4.7 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1413 | 1245 |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |

## Multimodal

- Grok 4.7: 28.8 (#107)
- Qwen2.5 72B Instruct: —

| Benchmark | Grok 4.7 | Qwen2.5 72B Instruct |
|---|---|---|
| Furniture Assembly | 20.8% | — |

## Multilingual

- Grok 4.7: 51.2 (#108)
- Qwen2.5 72B Instruct: 41.2 (#208)

| Benchmark | Grok 4.7 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1392 | 1252 |
| LMArena Chinese | 1476 | 1272 |
| LMArena Russian | 1396 | 1264 |
| LMArena French | — | 1279 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Spanish | — | 1255 |

## Instruction Following

- Grok 4.7: 74.3 (#98)
- Qwen2.5 72B Instruct: 65.7 (#216)

| Benchmark | Grok 4.7 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1406 | 1254 |
| IFEval | — | 80.6% |

## Long Context

- Grok 4.7: 43.2 (#97)
- Qwen2.5 72B Instruct: 38.9 (#183)

| Benchmark | Grok 4.7 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1416 | 1282 |

## Writing & Preference

- Grok 4.7: 70.1 (#23)
- Qwen2.5 72B Instruct: 46.9 (#210)

| Benchmark | Grok 4.7 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1397 | 1269 |
| LMArena Creative Writing | 1391 | 1221 |
| LMArena Multi-Turn | 1389 | 1272 |
| EQ-Bench Creative Writing | 2007 | — |
| WildBench | — | 80.2% |

## FAQ

### Is Grok 4.7 better than Qwen2.5 72B Instruct?

Grok 4.7 is the stronger model overall, scoring 46.6 to 31.5 on the Noometry Index.

### Which is cheaper, Grok 4.7 or Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct is cheaper. It lists at $1.40 per million input tokens and $5.60 per million output tokens; Grok 4.7 lists at $2 and $6.

### Is Grok 4.7 or Qwen2.5 72B Instruct better for coding?

Grok 4.7 scores higher on coding benchmarks: 55.0 versus 32.8 in the Noometry coding category.

### Which has the bigger context window?

Grok 4.7 does, with 500K tokens against 131K.

### How many benchmarks do Grok 4.7 and Qwen2.5 72B Instruct share?

12 benchmarks have published results for both models. Grok 4.7 has 21 scored results on Noometry and Qwen2.5 72B Instruct has 43.