# Grok 4.20 Multi-Agent vs Grok 4.3

> Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 43.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-4-20-multi-agent-vs-grok-4-3
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Grok 4.20 Multi-Agent scores higher in 7 categories and Grok 4.3 in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 4.3 leads 52.5 to 39.7.
- The biggest single-benchmark swing is NYT Connections (extended): 89.6% for Grok 4.20 Multi-Agent and 55.2% for Grok 4.3.
- Both cost about the same: $1.25 input and $2.50 output per million tokens.

## Snapshot

| | Grok 4.20 Multi-Agent | Grok 4.3 |
|---|---|---|
| Provider | xAI | xAI |
| Noometry Index | 45.5 | 43.6 |
| Rank | 62 | 80 |
| Context | 1M | 1M |
| Input $/M | $1.25 | $1.25 |
| Output $/M | $2.50 | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Grok 4.20 Multi-Agent: 42.4 (#91)
- Grok 4.3: 41.3 (#117)

| Benchmark | Grok 4.20 Multi-Agent | Grok 4.3 |
|---|---|---|
| LMArena Coding | 1458 | 1415 |
| LMArena WebDev | — | 1357 |
| SciCode | — | 47.3% |
| WeirdML | — | 49.9% |
| ALE-Bench | — | 944.17 |

## Agentic & Tool Use

- Grok 4.20 Multi-Agent: —
- Grok 4.3: 27.6 (#93)

| Benchmark | Grok 4.20 Multi-Agent | Grok 4.3 |
|---|---|---|
| LMArena Search | 1204 | 1165 |
| GDP.pdf | — | 8% |
| Vending-Bench 2 | — | 35.26 |

## Reasoning

- Grok 4.20 Multi-Agent: 42.4 (#44)
- Grok 4.3: 34.9 (#60)

| Benchmark | Grok 4.20 Multi-Agent | Grok 4.3 |
|---|---|---|
| NYT Connections (extended) | 89.6% | 55.2% |
| LMArena Hard Prompts | 1448 | 1397 |
| CritPt | — | 8% |
| Chess Puzzles | — | 25% |
| DTBench | — | 90.7% |
| LMCA | — | 38.3% |
| Epoch Capabilities Index | — | 149.13 |
| ForecastBench | — | 60.3 |

## Math

- Grok 4.20 Multi-Agent: 36.6 (#106)
- Grok 4.3: 45.8 (#60)

| Benchmark | Grok 4.20 Multi-Agent | Grok 4.3 |
|---|---|---|
| LMArena Math | 1441 | 1388 |
| FrontierMath (Tiers 1-3) | — | 42.8% |
| FrontierMath Tier 4 | — | 14.6% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| ProofBench | — | 11% |

## Knowledge

- Grok 4.20 Multi-Agent: 39.7 (#116)
- Grok 4.3: 52.5 (#57)

| Benchmark | Grok 4.20 Multi-Agent | Grok 4.3 |
|---|---|---|
| LMArena Expert | 1445 | 1385 |
| GPQA Diamond | — | 88.8% |
| SimpleQA Verified | — | 33.2% |

## Multimodal

- Grok 4.20 Multi-Agent: 39.8 (#44)
- Grok 4.3: 31.6 (#96)

| Benchmark | Grok 4.20 Multi-Agent | Grok 4.3 |
|---|---|---|
| LMArena Vision | 1259 | 1231 |
| Blueprint-Bench 2 | — | 0% |

## Multilingual

- Grok 4.20 Multi-Agent: 54.6 (#40)
- Grok 4.3: 50.7 (#114)

| Benchmark | Grok 4.20 Multi-Agent | Grok 4.3 |
|---|---|---|
| LMArena Non-English | 1440 | 1385 |
| LMArena Chinese | 1475 | 1423 |
| LMArena French | 1467 | 1412 |
| LMArena German | 1456 | 1395 |
| LMArena Japanese | 1405 | 1379 |
| LMArena Korean | 1416 | 1357 |
| LMArena Russian | 1457 | 1399 |
| LMArena Spanish | 1447 | 1402 |

## Instruction Following

- Grok 4.20 Multi-Agent: 75.0 (#80)
- Grok 4.3: 72.3 (#135)

| Benchmark | Grok 4.20 Multi-Agent | Grok 4.3 |
|---|---|---|
| LMArena Instruction Following | 1420 | 1366 |

## Long Context

- Grok 4.20 Multi-Agent: 43.7 (#84)
- Grok 4.3: 42.5 (#118)

| Benchmark | Grok 4.20 Multi-Agent | Grok 4.3 |
|---|---|---|
| LMArena Longer Query | 1430 | 1393 |

## Writing & Preference

- Grok 4.20 Multi-Agent: 64.1 (#57)
- Grok 4.3: 58.6 (#112)

| Benchmark | Grok 4.20 Multi-Agent | Grok 4.3 |
|---|---|---|
| LMArena Text | 1450 | 1397 |
| LMArena Creative Writing | 1435 | 1380 |
| LMArena Multi-Turn | 1451 | 1406 |
| EQ-Bench 4 | — | 1075 |

## FAQ

### Is Grok 4.20 Multi-Agent better than Grok 4.3?

Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 43.6 on the Noometry Index.

### Which is cheaper, Grok 4.20 Multi-Agent or Grok 4.3?

Grok 4.3 is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; Grok 4.20 Multi-Agent lists at $1.25 and $2.50.

### Is Grok 4.20 Multi-Agent or Grok 4.3 better for coding?

Grok 4.20 Multi-Agent scores higher on coding benchmarks: 42.4 versus 41.3 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1M tokens.

### How many benchmarks do Grok 4.20 Multi-Agent and Grok 4.3 share?

20 benchmarks have published results for both models. Grok 4.20 Multi-Agent has 20 scored results on Noometry and Grok 4.3 has 40.