# GPT-4o mini vs Grok 4.20 (Non-Reasoning)

> Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 25.4 on the Noometry Index. GPT-4o mini costs 6.0× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-4o-mini-vs-grok-4-20
- Last updated: 2026-10-10
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. GPT-4o mini scores higher in 0 categories and Grok 4.20 (Non-Reasoning) in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.2 to 8.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.9% for GPT-4o mini and 92.2% for Grok 4.20 (Non-Reasoning).
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 128K.

## Snapshot

| | GPT-4o mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Provider | OpenAI | xAI |
| Noometry Index | 25.4 | 48.5 |
| Rank | 337 | 48 |
| Context | 128K | 1M |
| Input $/M | $0.15 | $1.25 |
| Output $/M | $0.60 | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4o mini: 21.6 (#330)
- Grok 4.20 (Non-Reasoning): 41.8 (#104)

| Benchmark | GPT-4o mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| WeirdML | 11.8% | 52.3% |
| LMArena Coding | 1290 | 1458 |
| Aider Polyglot | 3.6% | — |
| LMArena WebDev | — | 1374 |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 1,150 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |

## Agentic & Tool Use

- GPT-4o mini: 27.2 (#95)
- Grok 4.20 (Non-Reasoning): 34.3 (#43)

| Benchmark | GPT-4o mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| τ²-bench Banking | — | 18% |
| BALROG | 17.4% | — |
| LMArena Search | — | 1189 |
| Vending-Bench 2 | — | 4,663 |

## Reasoning

- GPT-4o mini: 8.7 (#343)
- Grok 4.20 (Non-Reasoning): 52.2 (#30)

| Benchmark | GPT-4o mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| ARC-AGI-2 | 0% | 65.1% |
| Kagi LLM Benchmark | 28.8% | 75% |
| Chess Puzzles | 0% | 24% |
| LMArena Hard Prompts | 1267 | 1451 |
| DTBench | 54.4% | 90.1% |
| LMCA | 10.4% | 38.7% |
| Epoch Capabilities Index | 126.56 | 152.01 |
| SimpleBench | 10.7% | — |
| NYT Connections (extended) | — | 85.4% |
| ARC-AGI-1 | — | 89.5% |
| Thematic Generalization | — | 63.8% |
| LiveBench Reasoning | 32.8% | — |
| Mystery Game Puzzles | 12% | — |
| LiveBench Data Analysis | 50% | — |
| ForecastBench | — | 61.4 |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |

## Math

- GPT-4o mini: 9.9 (#307)
- Grok 4.20 (Non-Reasoning): 48.0 (#54)

| Benchmark | GPT-4o mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | 44.9% |
| OTIS Mock AIME 2024-2025 | 6.9% | 92.2% |
| LMArena Math | 1267 | 1455 |
| FrontierMath Tier 4 | — | 17.1% |
| ProofBench | — | 14% |
| Omni-MATH | 28% | — |
| LiveBench Math | 36.3% | — |
| MATH Level 5 | 52.6% | — |
| GSM8K | 91.3% | — |

## Knowledge

- GPT-4o mini: 17.7 (#279)
- Grok 4.20 (Non-Reasoning): 52.8 (#54)

| Benchmark | GPT-4o mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 37.7% | 89.3% |
| SimpleQA Verified | 8.3% | 30.2% |
| LMArena Expert | 1235 | 1440 |
| MMLU-Pro | 60.3% | — |
| Confabulations | 37.2% | — |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |

## Multimodal

- GPT-4o mini: 25.3 (#117)
- Grok 4.20 (Non-Reasoning): 33.2 (#88)

| Benchmark | GPT-4o mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | 1066 | 1263 |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1416 |

## Multilingual

- GPT-4o mini: 42.2 (#194)
- Grok 4.20 (Non-Reasoning): 54.7 (#38)

| Benchmark | GPT-4o mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1266 | 1440 |
| LMArena Chinese | 1264 | 1481 |
| LMArena French | 1296 | 1477 |
| LMArena German | 1272 | 1463 |
| LMArena Japanese | 1216 | 1450 |
| LMArena Korean | 1195 | 1417 |
| LMArena Russian | 1275 | 1457 |
| LMArena Spanish | 1276 | 1442 |

## Instruction Following

- GPT-4o mini: 62.1 (#234)
- Grok 4.20 (Non-Reasoning): 75.0 (#79)

| Benchmark | GPT-4o mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1259 | 1420 |
| LiveBench Instruction Following | 56.8% | — |
| IFEval | 78.2% | — |

## Long Context

- GPT-4o mini: 39.1 (#181)
- Grok 4.20 (Non-Reasoning): 45.4 (#33)

| Benchmark | GPT-4o mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1289 | 1436 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |

## Writing & Preference

- GPT-4o mini: 39.7 (#243)
- Grok 4.20 (Non-Reasoning): 65.9 (#42)

| Benchmark | GPT-4o mini | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1286 | 1451 |
| LMArena Creative Writing | 1268 | 1439 |
| EQ-Bench Creative Writing | 873 | 1574 |
| LMArena Multi-Turn | 1285 | 1456 |
| Short-Story Creative Writing | 67.2% | — |
| WildBench | 79.1% | — |
| LiveBench Language | 28.6% | — |

## FAQ

### Is GPT-4o mini better than Grok 4.20 (Non-Reasoning)?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 25.4 on the Noometry Index. GPT-4o mini costs 6.0× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

### Which is cheaper, GPT-4o mini or Grok 4.20 (Non-Reasoning)?

GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

### Is GPT-4o mini or Grok 4.20 (Non-Reasoning) better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 41.8 versus 21.6 in the Noometry coding category.

### Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 128K.

### How many benchmarks do GPT-4o mini and Grok 4.20 (Non-Reasoning) share?

30 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.