# Claude Sonnet 4.6 vs Gemini 3.1 Pro

> Side-by-side benchmark comparison for Claude Sonnet 4.6 and Gemini 3.1 Pro across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-sonnet-4-6-vs-gemini-3-1-pro
- Last updated: October 17, 2026

- Shared sourced benchmarks: 12
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Gemini 3.1 Pro leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Gemini 3.1 Pro has the higher overall point estimate 64.7 to 55.89. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in multimodal & grounded, where the averages are 58.7 for Claude Sonnet 4.6 and 80.1 for Gemini 3.1 Pro.
- The biggest single benchmark swing is Vibe Code Bench in Coding, with scores of 51.48% and 32.03%.
- Gemini 3.1 Pro is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Gemini 3.1 Pro also has the larger context window at 1M.

## Model Snapshot

| Property | Claude Sonnet 4.6 | Gemini 3.1 Pro |
|----------|----------|----------|
| Creator | Anthropic | Google |
| Type | Proprietary | Proprietary |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 200K | 1M |
| Overall Score | 55.89 | 64.7 |
| Benchmarks Covered | 28 | 30 |
| Pricing (input/output) | $3.00 / $15.00 | $2.00 / $12.00 |

## Category Breakdown

### Agentic

- Winner: Claude Sonnet 4.6
- Claude Sonnet 4.6 public-lane score: 46.3 (Supported · #55/128)
- Gemini 3.1 Pro public-lane score: 38.4 (Supported · #70/128)

| Benchmark | Claude Sonnet 4.6 | Gemini 3.1 Pro | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 59.1% | Coming soon | Coming soon |
| OSWorld-Verified | 72.1% | Coming soon | Coming soon |
| Claw-Eval | 67.8% | 57.8% | Claude Sonnet 4.6 |
| CyberGym | 65.2% | Coming soon | Coming soon |
| Gert Labs | 62.92% | 56.87% | Claude Sonnet 4.6 |
| OSWorld 2.0 | 8.3% | Coming soon | Coming soon |
| JobBench | 36.9% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 57.3% | 70.8% | Gemini 3.1 Pro |
| ApprenticeBench | 2% | Coming soon | Coming soon |
| MazeBench | 0% | 1% | Gemini 3.1 Pro |
| DeepSearchQA | Coming soon | 69.7% | Coming soon |
| τ²-bench results | Coming soon | 95.6% | Coming soon |
| ResearchClawBench | Coming soon | 13.3% | Coming soon |

### Coding

- Winner: Claude Sonnet 4.6
- Claude Sonnet 4.6 public-lane score: 44.7 (Supported · #54/150)
- Gemini 3.1 Pro public-lane score: 39.2 (Supported · #67/150)

| Benchmark | Claude Sonnet 4.6 | Gemini 3.1 Pro | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 79.6% | Coming soon | Coming soon |
| SWE-Rebench | 60.7% | Coming soon | Coming soon |
| React Native Evals | 80.6% | 78.9% | Claude Sonnet 4.6 |
| Terminal-Bench 2.0 | 59.1% | Coming soon | Coming soon |
| Vibe Code Bench | 51.48% | 32.03% | Claude Sonnet 4.6 |
| cursorBench31 | 48.8% | Coming soon | Coming soon |
| FrontierCode 1.1 Main | 24.3% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 82.1% | 88.5% | Gemini 3.1 Pro |
| SWE-bench (Vals) | 77.4% | 78.8% | Gemini 3.1 Pro |
| LiveCodeBench Pro | Coming soon | 82.9% | Coming soon |
| PostTrainBench v1.1 | Coming soon | 22.0% | Coming soon |

### Reasoning

- Winner: Not comparable
- Claude Sonnet 4.6 public-lane score: 62.8 (Unranked · 4 rankable rows)
- Gemini 3.1 Pro public-lane score: 58.2 (Unranked · 2 rankable rows)

| Benchmark | Claude Sonnet 4.6 | Gemini 3.1 Pro | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | 58.3% | 77.1% | Gemini 3.1 Pro |
| ARC-AGI-1 | 86.00% | Coming soon | Coming soon |
| ARC-AGI-3 | Coming soon | 0.4% | Coming soon |

### Multimodal & Grounded

- Winner: Directional only
- Claude Sonnet 4.6 public-lane score: 58.7 (#45/54)
- Gemini 3.1 Pro public-lane score: 80.1 (#17/54)

| Benchmark | Claude Sonnet 4.6 | Gemini 3.1 Pro | Winner |
|-----------|-----------|-----------|--------|
| CharXiv | 77.4% | 80.2% | Gemini 3.1 Pro |
| MMMU-Pro | Coming soon | 83.9% | Coming soon |
| ERQA | Coming soon | 69.4% | Coming soon |
| SimpleVQA | Coming soon | 72.4% | Coming soon |
| ScreenSpot Pro | Coming soon | 84.4% | Coming soon |
| ZeroBench | Coming soon | 29.0% | Coming soon |
| MedXpertQA (MM) | Coming soon | 81.3% | Coming soon |

### Knowledge

- Winner: Gemini 3.1 Pro
- Claude Sonnet 4.6 public-lane score: 55.4 (Supported · #58/184)
- Gemini 3.1 Pro public-lane score: 67.6 (Supported · #26/184)

| Benchmark | Claude Sonnet 4.6 | Gemini 3.1 Pro | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 89.9% | Coming soon | Coming soon |
| SuperGPQA | 95% | Coming soon | Coming soon |
| MMLU-Pro | 79.2% | Coming soon | Coming soon |
| HLE | 49% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 85.6% | 95.5% | Gemini 3.1 Pro |
| MMLU-Pro (Vals) | 87.3% | 91.0% | Gemini 3.1 Pro |
| GPQA-D | Coming soon | 94.3% | Coming soon |
| HLE w/o tools | Coming soon | 45.4% | Coming soon |
| HealthBench Hard | Coming soon | 20.6% | Coming soon |
| MedXpertQA (Text) | Coming soon | 71.5% | Coming soon |

### Instruction Following

- Winner: Not comparable
- Claude Sonnet 4.6 public-lane score: 48 (#99/148)
- Gemini 3.1 Pro public-lane score: Coming soon

### Mathematics

- Winner: Not comparable
- Claude Sonnet 4.6 public-lane score: Coming soon
- Gemini 3.1 Pro public-lane score: 65 (Unranked · 2 rankable rows)

| Benchmark | Claude Sonnet 4.6 | Gemini 3.1 Pro | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | Coming soon | 59.649% | Coming soon |
| FrontierMath v2 (Tier 4) | Coming soon | 26.829% | Coming soon |

## FAQ

### Which is better overall, Claude Sonnet 4.6 or Gemini 3.1 Pro?

Gemini 3.1 Pro has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between Claude Sonnet 4.6 and Gemini 3.1 Pro?

The widest category gap is in multimodal & grounded, where the averages are 58.7 for Claude Sonnet 4.6 and 80.1 for Gemini 3.1 Pro.

### How many benchmarks does Claude Sonnet 4.6 cover on BenchLM?

Claude Sonnet 4.6 currently has 28 sourced benchmark scores on BenchLM.

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

Gemini 3.1 Pro currently has 30 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Claude Sonnet 4.6 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-claude-sonnet-4-6)
- [Gemini 3.1 Pro vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-gemini-3-1-pro)
- [Claude Sonnet 4.6 vs GPT-6.1 Sol](/compare/claude-sonnet-4-6-vs-gpt-6-1-sol)
- [Gemini 3.1 Pro vs GPT-6.1 Sol](/compare/gemini-3-1-pro-vs-gpt-6-1-sol)

## Explore More

- [Claude Sonnet 4.6 profile](/models/claude-sonnet-4-6)
- [Gemini 3.1 Pro profile](/models/gemini-3-1-pro)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)