# Gemini 3.1 Pro vs Gemini 3.5 Flash

> Side-by-side benchmark comparison for Gemini 3.1 Pro and Gemini 3.5 Flash across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gemini-3-1-pro-vs-gemini-3-5-flash
- Last updated: October 2, 2026

- Shared sourced benchmarks: 14
- 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 65.09 to 63.95. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in agentic, where the averages are 39.3 for Gemini 3.1 Pro and 50.7 for Gemini 3.5 Flash.
- The biggest single benchmark swing is Vibe Code Bench in Coding, with scores of 32.03% and 48.68%.
- Gemini 3.5 Flash is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | Gemini 3.1 Pro | Gemini 3.5 Flash |
|----------|----------|----------|
| Creator | Google | Google |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1M |
| Overall Score | 65.09 | 63.95 |
| Benchmarks Covered | 29 | 27 |
| Pricing (input/output) | $2.00 / $12.00 | $1.50 / $9.00 |

## Category Breakdown

### Agentic

- Winner: Gemini 3.5 Flash
- Gemini 3.1 Pro public-lane score: 39.3 (Supported · #59/119)
- Gemini 3.5 Flash public-lane score: 50.7 (Supported · #42/119)

| Benchmark | Gemini 3.1 Pro | Gemini 3.5 Flash | Winner |
|-----------|-----------|-----------|--------|
| Claw-Eval | 57.8% | Coming soon | Coming soon |
| DeepSearchQA | 69.7% | Coming soon | Coming soon |
| τ²-bench results | 95.6% | Coming soon | Coming soon |
| Gert Labs | 56.87% | 61.85% | Gemini 3.5 Flash |
| ResearchClawBench | 13.3% | 18.0% | Gemini 3.5 Flash |
| Terminal-Bench 2.1 (Vals) | 70.8% | 74.2% | Gemini 3.5 Flash |
| Terminal-Bench 2.1 | Coming soon | 76.2% | Coming soon |
| MCP Atlas | Coming soon | 83.6% | Coming soon |
| Toolathlon | Coming soon | 56.5% | Coming soon |
| OSWorld-Verified | Coming soon | 78.4% | Coming soon |
| Finance Agent v2 | Coming soon | 57.9% | Coming soon |

### Coding

- Winner: Gemini 3.5 Flash
- Gemini 3.1 Pro public-lane score: 42.3 (Supported · #61/144)
- Gemini 3.5 Flash public-lane score: 52.3 (Supported · #39/144)

| Benchmark | Gemini 3.1 Pro | Gemini 3.5 Flash | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench Pro | 82.9% | Coming soon | Coming soon |
| React Native Evals | 78.9% | Coming soon | Coming soon |
| Vibe Code Bench | 32.03% | 48.68% | Gemini 3.5 Flash |
| LiveCodeBench (Vals) | 88.5% | 87.6% | Gemini 3.1 Pro |
| SWE-bench (Vals) | 78.8% | 78.8% | Tie |
| PostTrainBench v1.1 | 22.0% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 76.2% | Coming soon |
| SWE-bench Pro | Coming soon | 55.1% | Coming soon |
| cursorBench31 | Coming soon | 49.8% | Coming soon |
| CursorBench 3.2 | Coming soon | 48.8% | Coming soon |

### Reasoning

- Winner: Not comparable
- Gemini 3.1 Pro public-lane score: 54.4 (Unranked · 2 rankable rows)
- Gemini 3.5 Flash public-lane score: 62.8 (#20/27)

| Benchmark | Gemini 3.1 Pro | Gemini 3.5 Flash | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | 77.1% | 72.1% | Gemini 3.1 Pro |
| ARC-AGI-3 | 0.4% | Coming soon | Coming soon |
| MRCRv2 | Coming soon | 77.3% | Coming soon |
| MRCR 1M | Coming soon | 26.6% | Coming soon |

### Multimodal & Grounded

- Winner: Gemini 3.5 Flash
- Gemini 3.1 Pro public-lane score: 80.1 (#13/49)
- Gemini 3.5 Flash public-lane score: 87.8 (#6/49)

| Benchmark | Gemini 3.1 Pro | Gemini 3.5 Flash | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 83.9% | 83.6% | Gemini 3.1 Pro |
| CharXiv | 80.2% | 84.2% | Gemini 3.5 Flash |
| ERQA | 69.4% | Coming soon | Coming soon |
| SimpleVQA | 72.4% | Coming soon | Coming soon |
| ScreenSpot Pro | 84.4% | Coming soon | Coming soon |
| ZeroBench | 29.0% | Coming soon | Coming soon |
| MedXpertQA (MM) | 81.3% | Coming soon | Coming soon |
| Blueprint-Bench 2 | Coming soon | 33.6% | Coming soon |

### Knowledge

- Winner: Gemini 3.1 Pro
- Gemini 3.1 Pro public-lane score: 66.2 (Supported · #22/171)
- Gemini 3.5 Flash public-lane score: 64 (Supported · #30/171)

| Benchmark | Gemini 3.1 Pro | Gemini 3.5 Flash | Winner |
|-----------|-----------|-----------|--------|
| GPQA-D | 94.3% | 92.7% | Gemini 3.1 Pro |
| HLE w/o tools | 45.4% | Coming soon | Coming soon |
| HealthBench Hard | 20.6% | Coming soon | Coming soon |
| MedXpertQA (Text) | 71.5% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 95.5% | 92.7% | Gemini 3.1 Pro |
| MMLU-Pro (Vals) | 91.0% | 89.5% | Gemini 3.1 Pro |
| HLE | Coming soon | 40.2% | Coming soon |

### Instruction Following

- Winner: Not comparable
- Gemini 3.1 Pro public-lane score: Coming soon
- Gemini 3.5 Flash public-lane score: 84.1 (#43/125)

### Mathematics

- Winner: Not comparable
- Gemini 3.1 Pro public-lane score: 54.2 (Unranked · 2 rankable rows)
- Gemini 3.5 Flash public-lane score: 55.1 (Unranked · 2 rankable rows)

| Benchmark | Gemini 3.1 Pro | Gemini 3.5 Flash | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 36.900% | 38.966% | Gemini 3.5 Flash |
| FrontierMath v2 (Tier 4) | 16.700% | 14.583% | Gemini 3.1 Pro |

## FAQ

### Which is better overall, Gemini 3.1 Pro or Gemini 3.5 Flash?

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

### Where is the biggest gap between Gemini 3.1 Pro and Gemini 3.5 Flash?

The widest category gap is in agentic, where the averages are 39.3 for Gemini 3.1 Pro and 50.7 for Gemini 3.5 Flash.

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

Gemini 3.1 Pro currently has 29 sourced benchmark scores on BenchLM.

### How many benchmarks does Gemini 3.5 Flash cover on BenchLM?

Gemini 3.5 Flash currently has 27 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Gemini 3.1 Pro vs Gemini 3.5 Flash Cyber](/compare/gemini-3-1-pro-vs-gemini-3-5-flash-cyber)
- [Gemini 3.5 Flash vs Gemini 3.5 Flash Cyber](/compare/gemini-3-5-flash-vs-gemini-3-5-flash-cyber)
- [Gemini 3.1 Pro vs GPT-6 Astra](/compare/gemini-3-1-pro-vs-gpt-6-astra)
- [Gemini 3.5 Flash vs GPT-6 Astra](/compare/gemini-3-5-flash-vs-gpt-6-astra)

## Explore More

- [Gemini 3.1 Pro profile](/models/gemini-3-1-pro)
- [Gemini 3.5 Flash profile](/models/gemini-3-5-flash)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)