# Gemini 1.0 Pro vs Grok 4

> Grok 4 is the stronger model overall, scoring 48.1 to 27.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemini-1-0-pro-vs-grok-4
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Gemini 1.0 Pro scores higher in 0 categories and Grok 4 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4 leads 48.4 to 9.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for Gemini 1.0 Pro and 84% for Grok 4.

## Snapshot

| | Gemini 1.0 Pro | Grok 4 |
|---|---|---|
| Provider | Google | xAI |
| Noometry Index | 27.3 | 48.1 |
| Rank | 332 | 56 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- Gemini 1.0 Pro: 32.2 (#275)
- Grok 4: 50.3 (#46)

| Benchmark | Gemini 1.0 Pro | Grok 4 |
|---|---|---|
| LMArena Coding | 1108 | 1408 |
| Aider Polyglot | — | 79.6% |
| WeirdML | — | 45.7% |
| HumanEval+ | 55.5% | — |
| MBPP+ | 61.4% | — |

## Agentic & Tool Use

- Gemini 1.0 Pro: —
- Grok 4: 32.3 (#68)

| Benchmark | Gemini 1.0 Pro | Grok 4 |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 21.1% |
| Cybench | — | 43% |
| DeepResearch Bench | — | 47.3% |
| BALROG | — | 43.6% |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 66.6% |

## Reasoning

- Gemini 1.0 Pro: 17.1 (#296)
- Grok 4: 36.7 (#65)

| Benchmark | Gemini 1.0 Pro | Grok 4 |
|---|---|---|
| LMArena Hard Prompts | 1109 | 1409 |
| Epoch Capabilities Index | 117.04 | 146.44 |
| ARC-AGI-2 | — | 16% |
| SimpleBench | — | 60.5% |
| Kagi LLM Benchmark | — | 73.6% |
| ARC-AGI-1 | — | 66.7% |
| Chess Puzzles | — | 28% |
| DTBench | 45.9% | — |
| ForecastBench | — | 60.9 |

## Math

- Gemini 1.0 Pro: 9.3 (#321)
- Grok 4: 48.4 (#64)

| Benchmark | Gemini 1.0 Pro | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 84% |
| LMArena Math | 1132 | 1422 |
| Omni-MATH | — | 60.3% |
| MATH Level 5 | 11.2% | — |
| FrontierMath (Feb 2025 set) | — | 19.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Gemini 1.0 Pro: 15.6 (#291)
- Grok 4: 53.8 (#55)

| Benchmark | Gemini 1.0 Pro | Grok 4 |
|---|---|---|
| GPQA Diamond | 34% | 87% |
| LMArena Expert | 1059 | 1415 |
| MMLU-Pro | — | 85.1% |
| Confabulations | — | 12.4% |
| GPQA (HELM) | — | 72.7% |
| MMLU | 70% | — |

## Multimodal

- Gemini 1.0 Pro: —
- Grok 4: 33.7 (#94)

| Benchmark | Gemini 1.0 Pro | Grok 4 |
|---|---|---|
| LMArena Vision | — | 1210 |
| GeoBench | — | 45% |

## Multilingual

- Gemini 1.0 Pro: 33.4 (#252)
- Grok 4: 51.8 (#103)

| Benchmark | Gemini 1.0 Pro | Grok 4 |
|---|---|---|
| LMArena Non-English | 1138 | 1403 |
| LMArena Chinese | 1124 | 1427 |
| LMArena French | 1145 | 1418 |
| LMArena German | 1125 | 1429 |
| LMArena Japanese | 1023 | 1394 |
| LMArena Russian | 1186 | 1410 |
| LMArena Spanish | 1119 | 1420 |
| LMArena Korean | — | 1377 |

## Instruction Following

- Gemini 1.0 Pro: 57.6 (#267)
- Grok 4: 79.2 (#5)

| Benchmark | Gemini 1.0 Pro | Grok 4 |
|---|---|---|
| LMArena Instruction Following | 1114 | 1387 |
| IFEval | — | 94.9% |

## Long Context

- Gemini 1.0 Pro: 34.3 (#249)
- Grok 4: 63.1 (#4)

| Benchmark | Gemini 1.0 Pro | Grok 4 |
|---|---|---|
| LMArena Longer Query | 1132 | 1409 |
| Fiction.LiveBench | — | 94.4% |

## Writing & Preference

- Gemini 1.0 Pro: 36.0 (#264)
- Grok 4: 58.5 (#116)

| Benchmark | Gemini 1.0 Pro | Grok 4 |
|---|---|---|
| LMArena Text | 1149 | 1411 |
| LMArena Creative Writing | 1131 | 1397 |
| LMArena Multi-Turn | 1139 | 1416 |
| Short-Story Creative Writing | — | 76.9% |
| WildBench | — | 79.7% |

## FAQ

### Is Gemini 1.0 Pro better than Grok 4?

Grok 4 is the stronger model overall, scoring 48.1 to 27.3 on the Noometry Index.

### Is Gemini 1.0 Pro or Grok 4 better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 32.2 in the Noometry coding category.

### How many benchmarks do Gemini 1.0 Pro and Grok 4 share?

19 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and Grok 4 has 48.