Gemini 3.1 Pro PreviewvsGemini 2.5-Pro
Across 11 shared benchmarks, Gemini 3.1 Pro Preview leads overall: Gemini 3.1 Pro Preview wins 10, Gemini 2.5-Pro wins 1, with 0 ties and an average score difference of +30.56.
Google Deep Mind · 2026-02-20 · Multimodal model
Google Deep Mind · 2025-06-05 · Reasoning model
Benchmark scores
Grouped by capability, sorted by largest gap within each. 11 shared benchmarks.
General Knowledge
Gemini 3.1 Pro Preview 3/3| Benchmark | Gemini 3.1 Pro Preview | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| ARC-AGI-2 | 77.107 / 59Thinking High (No Tools) | 4.9044 / 59 | +72.20 |
| HLE | 51.4015 / 157Thinking High (With Tools) | 21.6097 / 157 | +29.80 |
| GPQA Diamond | 94.303 / 178Thinking High (No Tools) | 86.4041 / 178 | +7.90 |
Coding and Software Engineer
Gemini 3.1 Pro Preview 2/2| Benchmark | Gemini 3.1 Pro Preview | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| LiveCodeBench | 91.703 / 120Thinking High (With Tools) | 77.1034 / 120 | +14.60 |
| SWE-bench Verified | 80.6010 / 108Thinking High (With Tools) | 67.2068 / 108 | +13.40 |
Math and Reasoning
Gemini 3.1 Pro Preview 2/2| Benchmark | Gemini 3.1 Pro Preview | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| FrontierMath | 36.9011 / 60Thinking High (No Tools) | 1123 / 60 | +25.90 |
| FrontierMath - Tier 4 | 16.7020 / 80Normal (No Tools) | 2.1056 / 80Normal (No Tools) | +14.60 |
Agent Level Benchmark
Gemini 3.1 Pro Preview 1/1| Benchmark | Gemini 3.1 Pro Preview | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| τ²-Bench - Telecom | 99.301 / 35Thinking High (With Tools) | 5432 / 35 | +45.30 |
AI Agent - Information Search
Gemini 3.1 Pro Preview 1/1| Benchmark | Gemini 3.1 Pro Preview | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| BrowseComp | 85.903 / 45Thinking High (With Tools + Internet) | 7.8044 / 45 | +78.10 |
AI Agent - Tool Usage
Gemini 3.1 Pro Preview 1/1| Benchmark | Gemini 3.1 Pro Preview | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| Terminal Bench 2.0 | 68.508 / 46Thinking High (With Tools) | 32.6046 / 46 | +35.90 |
Multimodal Understanding
Gemini 2.5-Pro 1/1| Benchmark | Gemini 3.1 Pro Preview | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| MMMU | 80.5011 / 28Thinking High (No Tools) | 829 / 28 | -1.50 |
Specs
| Field | Gemini 3.1 Pro Preview | Gemini 2.5-Pro |
|---|---|---|
| Publisher | Google Deep Mind | Google Deep Mind |
| Release date | 2026-02-20 | 2025-06-05 |
| Model type | Multimodal model | Reasoning model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 1M | 1000K |
| Max output | 32K | 64K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Gemini 3.1 Pro Preview | Gemini 2.5-Pro |
|---|---|---|
| Text input | $2 / 1M tokens | Not public |
| Text output | $12 / 1M tokens | Not public |
One or both models have incomplete public pricing.
Summary
- Gemini 3.1 Pro Previewleads in:General Knowledge (3/3), Coding and Software Engineer (2/2), Math and Reasoning (2/2), Agent Level Benchmark (1/1), AI Agent - Information Search (1/1), AI Agent - Tool Usage (1/1)
- Gemini 2.5-Proleads in:Multimodal Understanding (1/1)
On average across the 11 shared benchmarks, Gemini 3.1 Pro Preview scores 30.56 higher.
Largest single-benchmark gap: BrowseComp — Gemini 3.1 Pro Preview 85.90 vs Gemini 2.5-Pro 7.80 (+78.10).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.