# Gemini 2.5 Pro vs Grok 4.20 (Non-Reasoning)

> Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 44.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-2-5-pro-vs-grok-4-20
- Last updated: 2026-10-10
- Shared benchmarks: 39

## Summary

- They share 39 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 6 categories and Grok 4.20 (Non-Reasoning) in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.2 to 28.8.
- The biggest single-benchmark swing is ARC-AGI-2: 4.9% for Gemini 2.5 Pro and 65.1% for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) is cheaper at $1.25 / $2.50 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
- Gemini 2.5 Pro accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Gemini 2.5 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Provider | Google | xAI |
| Noometry Index | 44.9 | 48.5 |
| Rank | 67 | 48 |
| Context | 1.05M | 1M |
| Input $/M | $1.25 | $1.25 |
| Output $/M | $10 | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 2.5 Pro: 42.8 (#86)
- Grok 4.20 (Non-Reasoning): 41.8 (#104)

| Benchmark | Gemini 2.5 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena WebDev | 1227 | 1374 |
| WeirdML | 54% | 52.3% |
| LMArena Coding | 1452 | 1458 |
| ALE-Bench | 785.52 | 1,150 |
| SWE-bench Verified | 57.6% | — |
| SWE-bench Verified (bash only) | 53.6% | — |
| Aider Polyglot | 83.1% | — |
| SciCode | 42.8% | — |
| GSO | 3.9% | — |
| LiveBench Coding | 85.9% | — |
| CadEval | 64% | — |
| AlgoTune | 1.51 | — |

## Agentic & Tool Use

- Gemini 2.5 Pro: 29.1 (#81)
- Grok 4.20 (Non-Reasoning): 34.3 (#43)

| Benchmark | Gemini 2.5 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| Terminal-Bench | 32.6% | 57.3% |
| τ²-bench Banking | 13.7% | 18% |
| LMArena Search | 1142 | 1189 |
| Vending-Bench 2 | 573.64 | 4,663 |
| GDPval | 23.3% | — |
| Remote Labor Index | 0.8% | — |
| TheAgentCompany | 30.3% | — |
| DeepResearch Bench | 42.8% | — |
| BALROG | 43.3% | — |
| METR Time Horizons | 55.4% | — |

## Reasoning

- Gemini 2.5 Pro: 28.8 (#85)
- Grok 4.20 (Non-Reasoning): 52.2 (#30)

| Benchmark | Gemini 2.5 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| ARC-AGI-2 | 4.9% | 65.1% |
| Kagi LLM Benchmark | 70.3% | 75% |
| ARC-AGI-1 | 41% | 89.5% |
| Chess Puzzles | 20% | 24% |
| LMArena Hard Prompts | 1455 | 1451 |
| DTBench | 82.4% | 90.1% |
| LMCA | 34.8% | 38.7% |
| Epoch Capabilities Index | 145.32 | 152.01 |
| ForecastBench | 61.3 | 61.4 |
| SimpleBench | 62.4% | — |
| NYT Connections (extended) | — | 85.4% |
| CritPt | 2% | — |
| EnigmaEval | 5.6% | — |
| Thematic Generalization | — | 63.8% |
| LiveBench Reasoning | 89.8% | — |
| LiveBench Data Analysis | 79.9% | — |
| LiveBench | 82.3% | — |

## Math

- Gemini 2.5 Pro: 31.9 (#191)
- Grok 4.20 (Non-Reasoning): 48.0 (#54)

| Benchmark | Gemini 2.5 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| FrontierMath (Tiers 1-3) | 24.6% | 44.9% |
| FrontierMath Tier 4 | 0% | 17.1% |
| OTIS Mock AIME 2024-2025 | 84.7% | 92.2% |
| LMArena Math | 1450 | 1455 |
| ProofBench | — | 14% |
| Omni-MATH | 41.6% | — |
| LiveBench Math | 90.2% | — |
| MATH Level 5 | 95.9% | — |
| FrontierMath (Feb 2025 set) | 14.1% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Gemini 2.5 Pro: 55.8 (#41)
- Grok 4.20 (Non-Reasoning): 52.8 (#54)

| Benchmark | Gemini 2.5 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| GPQA Diamond | 85.3% | 89.3% |
| LMArena Expert | 1452 | 1440 |
| Humanity's Last Exam | 21.6% | — |
| SimpleQA Verified | — | 30.2% |
| MMLU-Pro | 86.3% | — |
| Confabulations | 10.6% | — |
| Vectara Hallucination Rate | 7% | — |
| GPQA (HELM) | 74.9% | — |

## Multimodal

- Gemini 2.5 Pro: 44.5 (#16)
- Grok 4.20 (Non-Reasoning): 33.2 (#88)

| Benchmark | Gemini 2.5 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Vision | 1263 | 1263 |
| LMArena Document | 1421 | 1416 |
| GeoBench | 86% | — |
| VPCT | 48% | — |
| Blueprint-Bench 2 | — | 0% |
| SpatialViz-Bench | 44.7% | — |

## Multilingual

- Gemini 2.5 Pro: 55.5 (#30)
- Grok 4.20 (Non-Reasoning): 54.7 (#38)

| Benchmark | Gemini 2.5 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Non-English | 1452 | 1440 |
| LMArena Chinese | 1507 | 1481 |
| LMArena French | 1473 | 1477 |
| LMArena German | 1487 | 1463 |
| LMArena Japanese | 1462 | 1450 |
| LMArena Korean | 1435 | 1417 |
| LMArena Russian | 1460 | 1457 |
| LMArena Spanish | 1473 | 1442 |

## Instruction Following

- Gemini 2.5 Pro: 75.2 (#71)
- Grok 4.20 (Non-Reasoning): 75.0 (#79)

| Benchmark | Gemini 2.5 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Instruction Following | 1436 | 1420 |
| LiveBench Instruction Following | 80.6% | — |
| IFEval | 84% | — |

## Long Context

- Gemini 2.5 Pro: 59.7 (#5)
- Grok 4.20 (Non-Reasoning): 45.4 (#33)

| Benchmark | Gemini 2.5 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Longer Query | 1449 | 1436 |
| Fiction.LiveBench | 91.7% | — |
| CL-bench | — | 22.2% |
| CL-bench Life | — | 11.9% |

## Writing & Preference

- Gemini 2.5 Pro: 63.9 (#60)
- Grok 4.20 (Non-Reasoning): 65.9 (#42)

| Benchmark | Gemini 2.5 Pro | Grok 4.20 (Non-Reasoning) |
|---|---|---|
| LMArena Text | 1458 | 1451 |
| LMArena Creative Writing | 1453 | 1439 |
| EQ-Bench Creative Writing | 1421 | 1574 |
| LMArena Multi-Turn | 1453 | 1456 |
| Short-Story Creative Writing | 83.8% | — |
| WildBench | 85.7% | — |
| LiveBench Language | 67.8% | — |

## FAQ

### Is Gemini 2.5 Pro better than Grok 4.20 (Non-Reasoning)?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 44.9 on the Noometry Index.

### Which is cheaper, Gemini 2.5 Pro or Grok 4.20 (Non-Reasoning)?

Grok 4.20 (Non-Reasoning) is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

### Is Gemini 2.5 Pro or Grok 4.20 (Non-Reasoning) better for coding?

Gemini 2.5 Pro scores higher on coding benchmarks: 42.8 versus 41.8 in the Noometry coding category.

### Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 1M.

### How many benchmarks do Gemini 2.5 Pro and Grok 4.20 (Non-Reasoning) share?

39 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Grok 4.20 (Non-Reasoning) has 46.