# Gemini 3 Flash Preview vs Grok 4.20 (Non-Reasoning)

> Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 48.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-flash-preview-vs-grok-4-20
- Last updated: 2026-10-10
- Shared benchmarks: 41

## Summary

- They share 41 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 7 categories and Grok 4.20 (Non-Reasoning) in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where Gemini 3 Flash Preview leads 45.3 to 33.2.
- The biggest single-benchmark swing is SimpleQA Verified: 66.8% for Gemini 3 Flash Preview and 30.2% for Grok 4.20 (Non-Reasoning).
- Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
- Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Gemini 3 Flash Preview | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Provider | Google | xAI |
| Noometry Index | 52.3 | 48.5 |
| Rank | 33 | 48 |
| Context | 1.05M | 1M |
| Input $/M | $0.50 | $1.25 |
| Output $/M | $3 | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3 Flash Preview: 51.5 (#35)
- Grok 4.20 (Non-Reasoning): 41.8 (#104)

| Benchmark | Gemini 3 Flash Preview | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena WebDev | 1439 | 1374 |
| WeirdML | 61.6% | 52.3% |
| LMArena Coding | 1460 | 1458 |
| ALE-Bench | 1,367 | 1,150 |
| SWE-bench Verified | 75.4% | — |
| SWE-bench Verified (bash only) | 75.8% | — |
| SWE-bench Multilingual | 72.7% | — |
| GSO | 9.8% | — |

## Agentic & Tool Use

- Gemini 3 Flash Preview: 38.6 (#27)
- Grok 4.20 (Non-Reasoning): 34.3 (#43)

| Benchmark | Gemini 3 Flash Preview | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | 64.3% | 57.3% |
| τ²-bench Banking | 27.3% | 18% |
| LMArena Search | 1198 | 1189 |
| Vending-Bench 2 | 3,635 | 4,663 |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Retail | 76.8% | — |
| τ²-bench Telecom | 91.2% | — |
| DeepResearch Bench | 49.8% | — |
| BALROG | 48.1% | — |
| GDP.pdf | 10% | — |

## Reasoning

- Gemini 3 Flash Preview: 49.2 (#35)
- Grok 4.20 (Non-Reasoning): 52.2 (#30)

| Benchmark | Gemini 3 Flash Preview | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| ARC-AGI-2 | 33.6% | 65.1% |
| NYT Connections (extended) | 83.1% | 85.4% |
| ARC-AGI-1 | 84.7% | 89.5% |
| Chess Puzzles | 40% | 24% |
| LMArena Hard Prompts | 1465 | 1451 |
| DTBench | 89.1% | 90.1% |
| LMCA | 43.1% | 38.7% |
| Epoch Capabilities Index | 151.83 | 152.01 |
| ForecastBench | 58.5 | 61.4 |
| SimpleBench | 61.1% | — |
| Kagi LLM Benchmark | — | 75% |
| Thematic Generalization | — | 63.8% |
| Mystery Game Puzzles | 26% | — |

## Math

- Gemini 3 Flash Preview: 51.4 (#42)
- Grok 4.20 (Non-Reasoning): 48.0 (#54)

| Benchmark | Gemini 3 Flash Preview | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | 44.9% |
| FrontierMath Tier 4 | 17.1% | 17.1% |
| OTIS Mock AIME 2024-2025 | 95.6% | 92.2% |
| ProofBench | 15% | 14% |
| LMArena Math | 1472 | 1455 |
| MathArena Final-Answer Competitions | 67.6% | — |
| FrontierMath (Feb 2025 set) | 35.6% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Gemini 3 Flash Preview: 58.8 (#30)
- Grok 4.20 (Non-Reasoning): 52.8 (#54)

| Benchmark | Gemini 3 Flash Preview | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 89.4% | 89.3% |
| SimpleQA Verified | 66.8% | 30.2% |
| LMArena Expert | 1461 | 1440 |
| Vectara Hallucination Rate | 13.5% | — |

## Multimodal

- Gemini 3 Flash Preview: 45.3 (#15)
- Grok 4.20 (Non-Reasoning): 33.2 (#88)

| Benchmark | Gemini 3 Flash Preview | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | 1285 | 1263 |
| Blueprint-Bench 2 | 0% | 0% |
| LMArena Document | 1413 | 1416 |
| GeoBench | 88% | — |
| VPCT | 72.6% | — |

## Multilingual

- Gemini 3 Flash Preview: 55.9 (#26)
- Grok 4.20 (Non-Reasoning): 54.7 (#38)

| Benchmark | Gemini 3 Flash Preview | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1458 | 1440 |
| LMArena Chinese | 1510 | 1481 |
| LMArena French | 1478 | 1477 |
| LMArena German | 1497 | 1463 |
| LMArena Japanese | 1488 | 1450 |
| LMArena Korean | 1443 | 1417 |
| LMArena Russian | 1480 | 1457 |
| LMArena Spanish | 1470 | 1442 |

## Instruction Following

- Gemini 3 Flash Preview: 75.8 (#52)
- Grok 4.20 (Non-Reasoning): 75.0 (#79)

| Benchmark | Gemini 3 Flash Preview | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1437 | 1420 |

## Long Context

- Gemini 3 Flash Preview: 44.4 (#63)
- Grok 4.20 (Non-Reasoning): 45.4 (#33)

| Benchmark | Gemini 3 Flash Preview | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1452 | 1436 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |

## Writing & Preference

- Gemini 3 Flash Preview: 65.6 (#44)
- Grok 4.20 (Non-Reasoning): 65.9 (#42)

| Benchmark | Gemini 3 Flash Preview | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1466 | 1451 |
| LMArena Creative Writing | 1457 | 1439 |
| LMArena Multi-Turn | 1471 | 1456 |
| EQ-Bench Creative Writing | — | 1574 |

## FAQ

### Is Gemini 3 Flash Preview better than Grok 4.20 (Non-Reasoning)?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 48.5 on the Noometry Index.

### Which is cheaper, Gemini 3 Flash Preview or Grok 4.20 (Non-Reasoning)?

Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

### Is Gemini 3 Flash Preview or Grok 4.20 (Non-Reasoning) better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 51.5 versus 41.8 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 1M.

### How many benchmarks do Gemini 3 Flash Preview and Grok 4.20 (Non-Reasoning) share?

41 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.