# Grok 4.20 Multi-Agent vs Qwen1.5-72B

> Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-4-20-multi-agent-vs-qwen1-5-72b
- Last updated: 2026-10-12
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Grok 4.20 Multi-Agent scores higher in 8 categories and Qwen1.5-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 4.20 Multi-Agent leads 40.4 to 11.5.
- Qwen1.5-72B has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 4.20 Multi-Agent | Qwen1.5-72B |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 46.2 | 30.8 |
| Rank | 65 | 285 |
| Context | 1M | — |
| Input $/M | $1.25 | — |
| Output $/M | $2.50 | — |
| Weights | Proprietary | Open |

## Coding

- Grok 4.20 Multi-Agent: 43.0 (#92)
- Qwen1.5-72B: 31.9 (#277)

| Benchmark | Grok 4.20 Multi-Agent | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1457 | 1165 |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |

## Agentic & Tool Use

- Grok 4.20 Multi-Agent: —
- Qwen1.5-72B: —

| Benchmark | Grok 4.20 Multi-Agent | Qwen1.5-72B |
|---|---|---|
| LMArena Search | 1204 | — |

## Reasoning

- Grok 4.20 Multi-Agent: 43.9 (#48)
- Qwen1.5-72B: 22.2 (#203)

| Benchmark | Grok 4.20 Multi-Agent | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1448 | 1148 |
| NYT Connections (extended) | 89.6% | — |

## Math

- Grok 4.20 Multi-Agent: 39.4 (#104)
- Qwen1.5-72B: 33.2 (#205)

| Benchmark | Grok 4.20 Multi-Agent | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1442 | 1164 |

## Knowledge

- Grok 4.20 Multi-Agent: 40.4 (#119)
- Qwen1.5-72B: 11.5 (#300)

| Benchmark | Grok 4.20 Multi-Agent | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1445 | 1136 |
| GPQA Diamond | — | 28.8% |

## Multimodal

- Grok 4.20 Multi-Agent: 40.5 (#48)
- Qwen1.5-72B: —

| Benchmark | Grok 4.20 Multi-Agent | Qwen1.5-72B |
|---|---|---|
| LMArena Vision | 1259 | — |

## Multilingual

- Grok 4.20 Multi-Agent: 54.4 (#43)
- Qwen1.5-72B: 33.2 (#253)

| Benchmark | Grok 4.20 Multi-Agent | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1440 | 1135 |
| LMArena Chinese | 1475 | 1186 |
| LMArena French | 1466 | 1159 |
| LMArena German | 1456 | 1084 |
| LMArena Japanese | 1405 | 1061 |
| LMArena Korean | 1416 | 1050 |
| LMArena Russian | 1457 | 1104 |
| LMArena Spanish | 1447 | 1110 |

## Instruction Following

- Grok 4.20 Multi-Agent: 74.8 (#84)
- Qwen1.5-72B: 59.3 (#256)

| Benchmark | Grok 4.20 Multi-Agent | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1420 | 1141 |

## Long Context

- Grok 4.20 Multi-Agent: 43.7 (#88)
- Qwen1.5-72B: 35.1 (#243)

| Benchmark | Grok 4.20 Multi-Agent | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1431 | 1157 |

## Writing & Preference

- Grok 4.20 Multi-Agent: 64.0 (#59)
- Qwen1.5-72B: 37.3 (#258)

| Benchmark | Grok 4.20 Multi-Agent | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1450 | 1166 |
| LMArena Creative Writing | 1436 | 1137 |
| LMArena Multi-Turn | 1452 | 1160 |

## FAQ

### Is Grok 4.20 Multi-Agent better than Qwen1.5-72B?

Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 30.8 on the Noometry Index.

### Is Grok 4.20 Multi-Agent or Qwen1.5-72B better for coding?

Grok 4.20 Multi-Agent scores higher on coding benchmarks: 43.0 versus 31.9 in the Noometry coding category.

### How many benchmarks do Grok 4.20 Multi-Agent and Qwen1.5-72B share?

17 benchmarks have published results for both models. Grok 4.20 Multi-Agent has 20 scored results on Noometry and Qwen1.5-72B has 22.