# Gemini 3.1 Pro vs Grok 4.20

> Side-by-side benchmark comparison for Gemini 3.1 Pro and Grok 4.20 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gemini-3-1-pro-vs-grok-4-20-beta
- Last updated: September 10, 2026

- Shared sourced benchmarks: 20
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick Gemini 3.1 Pro if you want the stronger benchmark profile. Grok 4.20 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Gemini 3.1 Pro leads overall 69.95 to 67.13.
- The clearest category separation is in multimodal & grounded, where the averages are 79.2 for Gemini 3.1 Pro and 34.6 for Grok 4.20.
- The biggest single benchmark swing is Vibe Code Bench in Coding, with scores of 32.03% and 4.06%.
- Grok 4.20 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Grok 4.20 also has the larger context window at 2M.

## Model Snapshot

| Property | Gemini 3.1 Pro | Grok 4.20 |
|----------|----------|----------|
| Creator | Google | xAI |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 2M |
| Overall Score | 69.95 | 67.13 |
| Benchmarks Covered | 28 | 23 |
| Pricing (input/output) | $2.00 / $12.00 | $2.00 / $6.00 |

## Category Breakdown

### Agentic

- Winner: Gemini 3.1 Pro
- Gemini 3.1 Pro public-lane score: 38.9 (Supported · #121/152)
- Grok 4.20 public-lane score: 26.7 (Supported · #145/152)

| Benchmark | Gemini 3.1 Pro | Grok 4.20 | Winner |
|-----------|-----------|-----------|--------|
| Claw-Eval | 57.8% | Coming soon | Coming soon |
| DeepSearchQA | 69.7% | 62.8% | Gemini 3.1 Pro |
| τ²-bench results | 95.6% | Coming soon | Coming soon |
| Gert Labs | 56.87% | 38.36% | Gemini 3.1 Pro |
| ResearchClawBench | 13.3% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 70.8% | 44.2% | Gemini 3.1 Pro |
| Terminal-Bench 2.0 | Coming soon | 47.1% | Coming soon |

### Coding

- Winner: Gemini 3.1 Pro
- Gemini 3.1 Pro public-lane score: 46.3 (Supported · #82/151)
- Grok 4.20 public-lane score: 28.2 (Supported · #141/151)

| Benchmark | Gemini 3.1 Pro | Grok 4.20 | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench Pro | 82.9% | 74.2% | Gemini 3.1 Pro |
| React Native Evals | 78.9% | Coming soon | Coming soon |
| Vibe Code Bench | 32.03% | 4.06% | Gemini 3.1 Pro |
| LiveCodeBench (Vals) | 88.5% | 84.3% | Gemini 3.1 Pro |
| SWE-bench (Vals) | 78.8% | 72.2% | Gemini 3.1 Pro |
| SWE-bench Verified | Coming soon | 76.7% | Coming soon |
| SWE-bench Pro | Coming soon | 51.8% | Coming soon |

### Multimodal & Grounded

- Winner: Gemini 3.1 Pro
- Gemini 3.1 Pro public-lane score: 79.2 (#12/48)
- Grok 4.20 public-lane score: 34.6 (#43/48)

| Benchmark | Gemini 3.1 Pro | Grok 4.20 | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 83.9% | 75.2% | Gemini 3.1 Pro |
| CharXiv | 80.2% | 60.9% | Gemini 3.1 Pro |
| ERQA | 69.4% | 54.1% | Gemini 3.1 Pro |
| SimpleVQA | 72.4% | 57.4% | Gemini 3.1 Pro |
| ScreenSpot Pro | 84.4% | Coming soon | Coming soon |
| ZeroBench | 29.0% | Coming soon | Coming soon |
| MedXpertQA (MM) | 81.3% | 65.8% | Gemini 3.1 Pro |

### Reasoning

- Winner: Coming soon
- Gemini 3.1 Pro public-lane score: 50.6 (Unranked · 2 rankable rows)
- Grok 4.20 public-lane score: 34.2 (Unranked · 2 rankable rows)

| Benchmark | Gemini 3.1 Pro | Grok 4.20 | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | 77.1% | 53.3% | Gemini 3.1 Pro |
| ARC-AGI-3 | 0.4% | 0.1% | Gemini 3.1 Pro |

### Knowledge

- Winner: Gemini 3.1 Pro
- Gemini 3.1 Pro public-lane score: 66.1 (Supported · #21/183)
- Grok 4.20 public-lane score: 49.4 (Supported · #85/183)

| Benchmark | Gemini 3.1 Pro | Grok 4.20 | Winner |
|-----------|-----------|-----------|--------|
| GPQA-D | 94.3% | 88.5% | Gemini 3.1 Pro |
| HLE w/o tools | 45.4% | 31.6% | Gemini 3.1 Pro |
| HealthBench Hard | 20.6% | 20.3% | Gemini 3.1 Pro |
| MedXpertQA (Text) | 71.5% | 50.2% | Gemini 3.1 Pro |
| GPQA Diamond (Vals) | 95.5% | 88.6% | Gemini 3.1 Pro |
| MMLU-Pro (Vals) | 91.0% | 86.3% | Gemini 3.1 Pro |

### Mathematics

- Winner: Coming soon
- Gemini 3.1 Pro public-lane score: 54.3 (Unranked · 2 rankable rows)
- Grok 4.20 public-lane score: Coming soon

| Benchmark | Gemini 3.1 Pro | Grok 4.20 | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 36.900% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 16.700% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Gemini 3.1 Pro or Grok 4.20?

Gemini 3.1 Pro is ahead overall on BenchLM right now.

### Where is the biggest gap between Gemini 3.1 Pro and Grok 4.20?

The widest category gap is in multimodal & grounded, where the averages are 79.2 for Gemini 3.1 Pro and 34.6 for Grok 4.20.

### How many benchmarks does Gemini 3.1 Pro cover on BenchLM?

Gemini 3.1 Pro currently has 28 sourced benchmark scores on BenchLM.

### How many benchmarks does Grok 4.20 cover on BenchLM?

Grok 4.20 currently has 23 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Gemini 3.1 Pro vs Grok 4.20 Multi-agent](/compare/gemini-3-1-pro-vs-grok-4-20-multi-agent-beta)
- [Grok 4.20 vs Grok 4.20 Multi-agent](/compare/grok-4-20-beta-vs-grok-4-20-multi-agent-beta)
- [Gemini 3.1 Pro vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-gemini-3-1-pro)
- [Grok 4.20 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-grok-4-20-beta)

## Explore More

- [Gemini 3.1 Pro profile](/models/gemini-3-1-pro)
- [Grok 4.20 profile](/models/grok-4-20-beta)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)