# GPT-5.4 mini vs Grok 4.20 Multi-Agent

> Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 45.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-4-mini-vs-grok-4-20-multi-agent
- Last updated: 2026-10-12
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. GPT-5.4 mini scores higher in 4 categories and Grok 4.20 Multi-Agent in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 Multi-Agent leads 43.9 to 30.4.
- The biggest single-benchmark swing is NYT Connections (extended): 61.8% for GPT-5.4 mini and 89.6% for Grok 4.20 Multi-Agent.
- Grok 4.20 Multi-Agent is cheaper at $1.25 / $2.50 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- Grok 4.20 Multi-Agent accepts more context: 1M tokens versus 400K.

## Snapshot

| | GPT-5.4 mini | Grok 4.20 Multi-Agent |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 45.0 | 46.2 |
| Rank | 76 | 65 |
| Context | 400K | 1M |
| Input $/M | $0.75 | $1.25 |
| Output $/M | $4.50 | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.4 mini: 45.2 (#72)
- Grok 4.20 Multi-Agent: 43.0 (#92)

| Benchmark | GPT-5.4 mini | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Coding | 1438 | 1457 |
| FrontierCode | 27% | — |
| LMArena WebDev | 1397 | — |
| SciCode | 49.9% | — |
| WeirdML | 60.3% | — |
| ALE-Bench | 1,189 | — |

## Agentic & Tool Use

- GPT-5.4 mini: 29.9 (#81)
- Grok 4.20 Multi-Agent: —

| Benchmark | GPT-5.4 mini | Grok 4.20 Multi-Agent |
|---|---|---|
| DeepResearch Bench | 36.3% | — |
| LMArena Search | — | 1204 |

## Reasoning

- GPT-5.4 mini: 30.4 (#85)
- Grok 4.20 Multi-Agent: 43.9 (#48)

| Benchmark | GPT-5.4 mini | Grok 4.20 Multi-Agent |
|---|---|---|
| NYT Connections (extended) | 61.8% | 89.6% |
| LMArena Hard Prompts | 1424 | 1448 |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 10% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| Mystery Game Puzzles | 11% | — |
| DTBench | 80% | — |
| LMCA | 40.8% | — |
| Epoch Capabilities Index | 148.84 | — |
| ForecastBench | 57 | — |

## Math

- GPT-5.4 mini: 45.5 (#75)
- Grok 4.20 Multi-Agent: 39.4 (#104)

| Benchmark | GPT-5.4 mini | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Math | 1419 | 1442 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 21% | — |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GPT-5.4 mini: 51.5 (#67)
- Grok 4.20 Multi-Agent: 40.4 (#119)

| Benchmark | GPT-5.4 mini | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Expert | 1435 | 1445 |
| GPQA Diamond | 86.9% | — |
| SimpleQA Verified | 29.4% | — |
| Vectara Hallucination Rate | 5.5% | — |

## Multimodal

- GPT-5.4 mini: 39.7 (#56)
- Grok 4.20 Multi-Agent: 40.5 (#48)

| Benchmark | GPT-5.4 mini | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Vision | 1245 | 1259 |

## Multilingual

- GPT-5.4 mini: 51.9 (#96)
- Grok 4.20 Multi-Agent: 54.4 (#43)

| Benchmark | GPT-5.4 mini | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Non-English | 1405 | 1440 |
| LMArena Chinese | 1446 | 1475 |
| LMArena French | 1440 | 1466 |
| LMArena German | 1409 | 1456 |
| LMArena Japanese | 1374 | 1405 |
| LMArena Korean | 1368 | 1416 |
| LMArena Russian | 1417 | 1457 |
| LMArena Spanish | 1405 | 1447 |

## Instruction Following

- GPT-5.4 mini: 74.1 (#102)
- Grok 4.20 Multi-Agent: 74.8 (#84)

| Benchmark | GPT-5.4 mini | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Instruction Following | 1405 | 1420 |

## Long Context

- GPT-5.4 mini: 43.0 (#112)
- Grok 4.20 Multi-Agent: 43.7 (#88)

| Benchmark | GPT-5.4 mini | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Longer Query | 1407 | 1431 |

## Writing & Preference

- GPT-5.4 mini: 64.0 (#58)
- Grok 4.20 Multi-Agent: 64.0 (#59)

| Benchmark | GPT-5.4 mini | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Text | 1412 | 1450 |
| LMArena Creative Writing | 1370 | 1436 |
| LMArena Multi-Turn | 1429 | 1452 |
| EQ-Bench Creative Writing | 1665 | — |

## FAQ

### Is GPT-5.4 mini better than Grok 4.20 Multi-Agent?

Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 45.0 on the Noometry Index.

### Which is cheaper, GPT-5.4 mini or Grok 4.20 Multi-Agent?

Grok 4.20 Multi-Agent is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.

### Is GPT-5.4 mini or Grok 4.20 Multi-Agent better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 43.0 in the Noometry coding category.

### Which has the bigger context window?

Grok 4.20 Multi-Agent does, with 1M tokens against 400K.

### How many benchmarks do GPT-5.4 mini and Grok 4.20 Multi-Agent share?

19 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Grok 4.20 Multi-Agent has 20.