# Gemini 3.6 Flash vs Grok 4.20 (Non-Reasoning)

> Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 48.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-3-6-flash-vs-grok-4-20
- Last updated: 2026-10-10
- Shared benchmarks: 37

## Summary

- They share 37 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 8 categories and Grok 4.20 (Non-Reasoning) in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.6 Flash leads 67.8 to 52.8.
- The biggest single-benchmark swing is SimpleQA Verified: 66.2% for Gemini 3.6 Flash and 30.2% for Grok 4.20 (Non-Reasoning).
- Both cost about the same: $0.75 input and $3.75 output per million tokens.
- Gemini 3.6 Flash accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Gemini 3.6 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Provider | Google | xAI |
| Noometry Index | 54.1 | 48.5 |
| Rank | 30 | 48 |
| Context | 1.05M | 1M |
| Input $/M | $0.75 | $1.25 |
| Output $/M | $3.75 | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 3.6 Flash: 49.6 (#45)
- Grok 4.20 (Non-Reasoning): 41.8 (#104)

| Benchmark | Gemini 3.6 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena WebDev | 1536 | 1374 |
| WeirdML | 56.1% | 52.3% |
| LMArena Coding | 1492 | 1458 |
| ALE-Bench | 715.52 | 1,150 |
| DeepSWE | 46.7% | — |
| FrontierCode | 34.4% | — |
| SciCode | 52.7% | — |

## Agentic & Tool Use

- Gemini 3.6 Flash: 32.4 (#56)
- Grok 4.20 (Non-Reasoning): 34.3 (#43)

| Benchmark | Gemini 3.6 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | — | 57.3% |
| APEX-Agents | 46.9% | — |
| τ²-bench Banking | — | 18% |
| GDP.pdf | 14% | — |
| LMArena Search | — | 1189 |
| Vending-Bench 2 | — | 4,663 |

## Reasoning

- Gemini 3.6 Flash: 58.9 (#20)
- Grok 4.20 (Non-Reasoning): 52.2 (#30)

| Benchmark | Gemini 3.6 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| ARC-AGI-2 | 60.4% | 65.1% |
| NYT Connections (extended) | 89% | 85.4% |
| ARC-AGI-1 | 91.2% | 89.5% |
| Chess Puzzles | 43% | 24% |
| LMArena Hard Prompts | 1486 | 1451 |
| DTBench | 95.5% | 90.1% |
| LMCA | 44.9% | 38.7% |
| Epoch Capabilities Index | 154.36 | 152.01 |
| Kagi LLM Benchmark | — | 75% |
| CritPt | 10.6% | — |
| Thematic Generalization | — | 63.8% |
| Mystery Game Puzzles | 30% | — |
| ForecastBench | — | 61.4 |

## Math

- Gemini 3.6 Flash: 57.0 (#33)
- Grok 4.20 (Non-Reasoning): 48.0 (#54)

| Benchmark | Gemini 3.6 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| FrontierMath (Tiers 1-3) | 58.9% | 44.9% |
| FrontierMath Tier 4 | 22% | 17.1% |
| OTIS Mock AIME 2024-2025 | 94.2% | 92.2% |
| ProofBench | 36% | 14% |
| LMArena Math | 1504 | 1455 |
| MathArena Final-Answer Competitions | 70.8% | — |

## Knowledge

- Gemini 3.6 Flash: 67.8 (#7)
- Grok 4.20 (Non-Reasoning): 52.8 (#54)

| Benchmark | Gemini 3.6 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 94.1% | 89.3% |
| SimpleQA Verified | 66.2% | 30.2% |
| LMArena Expert | 1489 | 1440 |

## Multimodal

- Gemini 3.6 Flash: 38.7 (#55)
- Grok 4.20 (Non-Reasoning): 33.2 (#88)

| Benchmark | Gemini 3.6 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | 1297 | 1263 |
| Blueprint-Bench 2 | 31.2% | 0% |
| LMArena Document | 1456 | 1416 |
| Furniture Assembly | 23.3% | — |

## Multilingual

- Gemini 3.6 Flash: 56.8 (#17)
- Grok 4.20 (Non-Reasoning): 54.7 (#38)

| Benchmark | Gemini 3.6 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1470 | 1440 |
| LMArena Chinese | 1530 | 1481 |
| LMArena French | 1501 | 1477 |
| LMArena German | 1478 | 1463 |
| LMArena Japanese | 1477 | 1450 |
| LMArena Korean | 1435 | 1417 |
| LMArena Russian | 1490 | 1457 |
| LMArena Spanish | 1477 | 1442 |

## Instruction Following

- Gemini 3.6 Flash: 77.2 (#27)
- Grok 4.20 (Non-Reasoning): 75.0 (#79)

| Benchmark | Gemini 3.6 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1467 | 1420 |

## Long Context

- Gemini 3.6 Flash: 45.1 (#47)
- Grok 4.20 (Non-Reasoning): 45.4 (#33)

| Benchmark | Gemini 3.6 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1475 | 1436 |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |

## Writing & Preference

- Gemini 3.6 Flash: 68.3 (#26)
- Grok 4.20 (Non-Reasoning): 65.9 (#42)

| Benchmark | Gemini 3.6 Flash | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1478 | 1451 |
| LMArena Creative Writing | 1464 | 1439 |
| EQ-Bench Creative Writing | 1604 | 1574 |
| LMArena Multi-Turn | 1481 | 1456 |

## FAQ

### Is Gemini 3.6 Flash better than Grok 4.20 (Non-Reasoning)?

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 48.5 on the Noometry Index.

### Which is cheaper, Gemini 3.6 Flash or Grok 4.20 (Non-Reasoning)?

Gemini 3.6 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

### Is Gemini 3.6 Flash or Grok 4.20 (Non-Reasoning) better for coding?

Gemini 3.6 Flash scores higher on coding benchmarks: 49.6 versus 41.8 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.6 Flash does, with 1.05M tokens against 1M.

### How many benchmarks do Gemini 3.6 Flash and Grok 4.20 (Non-Reasoning) share?

37 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.