# Grok 4.20 Multi-Agent vs Qwen2-72B

> Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-4-20-multi-agent-vs-qwen2-72b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Grok 4.20 Multi-Agent scores higher in 8 categories and Qwen2-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok 4.20 Multi-Agent leads 64.1 to 41.0.
- Qwen2-72B has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 4.20 Multi-Agent | Qwen2-72B |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 45.5 | 29.5 |
| Rank | 62 | 294 |
| Context | 1M | — |
| Input $/M | $1.25 | — |
| Output $/M | $2.50 | — |
| Weights | Proprietary | Open |

## Coding

- Grok 4.20 Multi-Agent: 42.4 (#91)
- Qwen2-72B: 28.7 (#303)

| Benchmark | Grok 4.20 Multi-Agent | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1458 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- Grok 4.20 Multi-Agent: —
- Qwen2-72B: 16.9 (#138)

| Benchmark | Grok 4.20 Multi-Agent | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| LMArena Search | 1204 | — |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Grok 4.20 Multi-Agent: 42.4 (#44)
- Qwen2-72B: 22.2 (#184)

| Benchmark | Grok 4.20 Multi-Agent | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1448 | 1191 |
| NYT Connections (extended) | 89.6% | — |
| Epoch Capabilities Index | — | 125.27 |

## Math

- Grok 4.20 Multi-Agent: 36.6 (#106)
- Qwen2-72B: 27.9 (#232)

| Benchmark | Grok 4.20 Multi-Agent | Qwen2-72B |
|---|---|---|
| LMArena Math | 1441 | 1235 |
| MATH Level 5 | — | 39.1% |

## Knowledge

- Grok 4.20 Multi-Agent: 39.7 (#116)
- Qwen2-72B: 21.2 (#270)

| Benchmark | Grok 4.20 Multi-Agent | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1445 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |

## Multimodal

- Grok 4.20 Multi-Agent: 39.8 (#44)
- Qwen2-72B: —

| Benchmark | Grok 4.20 Multi-Agent | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1259 | — |

## Multilingual

- Grok 4.20 Multi-Agent: 54.6 (#40)
- Qwen2-72B: 36.0 (#239)

| Benchmark | Grok 4.20 Multi-Agent | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1440 | 1176 |
| LMArena Chinese | 1475 | 1240 |
| LMArena French | 1467 | 1169 |
| LMArena German | 1456 | 1151 |
| LMArena Japanese | 1405 | 1111 |
| LMArena Korean | 1416 | 1083 |
| LMArena Russian | 1457 | 1169 |
| LMArena Spanish | 1447 | 1168 |

## Instruction Following

- Grok 4.20 Multi-Agent: 75.0 (#80)
- Qwen2-72B: 62.0 (#236)

| Benchmark | Grok 4.20 Multi-Agent | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1420 | 1181 |

## Long Context

- Grok 4.20 Multi-Agent: 43.7 (#84)
- Qwen2-72B: 36.1 (#230)

| Benchmark | Grok 4.20 Multi-Agent | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1430 | 1193 |

## Writing & Preference

- Grok 4.20 Multi-Agent: 64.1 (#57)
- Qwen2-72B: 41.0 (#236)

| Benchmark | Grok 4.20 Multi-Agent | Qwen2-72B |
|---|---|---|
| LMArena Text | 1450 | 1203 |
| LMArena Creative Writing | 1435 | 1181 |
| LMArena Multi-Turn | 1451 | 1195 |

## FAQ

### Is Grok 4.20 Multi-Agent better than Qwen2-72B?

Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 29.5 on the Noometry Index.

### Is Grok 4.20 Multi-Agent or Qwen2-72B better for coding?

Grok 4.20 Multi-Agent scores higher on coding benchmarks: 42.4 versus 28.7 in the Noometry coding category.

### How many benchmarks do Grok 4.20 Multi-Agent and Qwen2-72B share?

17 benchmarks have published results for both models. Grok 4.20 Multi-Agent has 20 scored results on Noometry and Qwen2-72B has 26.