# Grok-2 (Dec 2024) vs Grok 4.20 Multi-Agent

> Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-2-vs-grok-4-20-multi-agent
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 0 categories and Grok 4.20 Multi-Agent in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 Multi-Agent leads 43.9 to 16.9.

## Snapshot

| | Grok-2 (Dec 2024) | Grok 4.20 Multi-Agent |
|---|---|---|
| Provider | xAI | xAI |
| Noometry Index | 33.7 | 46.2 |
| Rank | 239 | 65 |
| Context | — | 1M |
| Input $/M | — | $1.25 |
| Output $/M | — | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Grok-2 (Dec 2024): 33.3 (#258)
- Grok 4.20 Multi-Agent: 43.0 (#92)

| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Coding | 1287 | 1457 |
| WeirdML | 22.2% | — |
| LiveBench Coding | 46.4% | — |

## Agentic & Tool Use

- Grok-2 (Dec 2024): —
- Grok 4.20 Multi-Agent: —

| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Search | — | 1204 |

## Reasoning

- Grok-2 (Dec 2024): 16.9 (#299)
- Grok 4.20 Multi-Agent: 43.9 (#48)

| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Hard Prompts | 1272 | 1448 |
| SimpleBench | 22.7% | — |
| NYT Connections (extended) | — | 89.6% |
| LiveBench Reasoning | 54.8% | — |
| DTBench | 65.2% | — |
| LiveBench Data Analysis | 54.5% | — |
| Epoch Capabilities Index | 130.48 | — |
| LiveBench | 54.3% | — |

## Math

- Grok-2 (Dec 2024): 20.8 (#284)
- Grok 4.20 Multi-Agent: 39.4 (#104)

| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Math | 1283 | 1442 |
| OTIS Mock AIME 2024-2025 | 11.5% | — |
| LiveBench Math | 54.9% | — |
| MATH Level 5 | 63.5% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |

## Knowledge

- Grok-2 (Dec 2024): 29.8 (#233)
- Grok 4.20 Multi-Agent: 40.4 (#119)

| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Expert | 1254 | 1445 |
| GPQA Diamond | 53.8% | — |
| Confabulations | 20.1% | — |

## Multimodal

- Grok-2 (Dec 2024): —
- Grok 4.20 Multi-Agent: 40.5 (#48)

| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Vision | — | 1259 |

## Multilingual

- Grok-2 (Dec 2024): 43.1 (#188)
- Grok 4.20 Multi-Agent: 54.4 (#43)

| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Non-English | 1282 | 1440 |
| LMArena Chinese | 1289 | 1475 |
| LMArena French | 1318 | 1466 |
| LMArena German | 1287 | 1456 |
| LMArena Japanese | 1244 | 1405 |
| LMArena Korean | 1237 | 1416 |
| LMArena Russian | 1286 | 1457 |
| LMArena Spanish | 1281 | 1447 |

## Instruction Following

- Grok-2 (Dec 2024): 66.9 (#202)
- Grok 4.20 Multi-Agent: 74.8 (#84)

| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Instruction Following | 1270 | 1420 |
| LiveBench Instruction Following | 69.6% | — |

## Long Context

- Grok-2 (Dec 2024): 38.8 (#190)
- Grok 4.20 Multi-Agent: 43.7 (#88)

| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Longer Query | 1276 | 1431 |

## Writing & Preference

- Grok-2 (Dec 2024): 48.6 (#198)
- Grok 4.20 Multi-Agent: 64.0 (#59)

| Benchmark | Grok-2 (Dec 2024) | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Text | 1305 | 1450 |
| LMArena Creative Writing | 1284 | 1436 |
| LMArena Multi-Turn | 1290 | 1452 |
| Short-Story Creative Writing | 63.6% | — |
| LiveBench Language | 45.6% | — |

## FAQ

### Is Grok-2 (Dec 2024) better than Grok 4.20 Multi-Agent?

Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 33.7 on the Noometry Index.

### Is Grok-2 (Dec 2024) or Grok 4.20 Multi-Agent better for coding?

Grok 4.20 Multi-Agent scores higher on coding benchmarks: 43.0 versus 33.3 in the Noometry coding category.

### How many benchmarks do Grok-2 (Dec 2024) and Grok 4.20 Multi-Agent share?

17 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Grok 4.20 Multi-Agent has 20.