Gemini 3.1 Pro PreviewvsClaude Opus 4.6
Across 18 shared benchmarks, Gemini 3.1 Pro Preview leads overall: Gemini 3.1 Pro Preview wins 11, Claude Opus 4.6 wins 6, with 1 ties and an average score difference of +2.37.
Gemini 3.1 Pro Preview
Google Deep Mind · 2026-02-20 · Multimodal model
Claude Opus 4.6
Anthropic · 2026-02-05 · Reasoning model
Gemini 3.1 Pro Preview11 wins(61%)Ties1(33%)6 winsClaude Opus 4.6
Benchmark scores
Grouped by capability, sorted by largest gap within each. 18 shared benchmarks.
General Knowledge
Gemini 3.1 Pro Preview 4/6| Benchmark | Gemini 3.1 Pro Preview | Claude Opus 4.6 | Diff |
|---|---|---|---|
| ARC-AGI-2 | 77.108 / 61Thinking High (No Tools) | 66.3016 / 61Extended (no tools) | +10.80 |
| LiveBench | 79.933 / 115Thinking High (No Tools) | 76.338 / 115Thinking High (No Tools) | +3.60 |
| GPQA Diamond | 94.303 / 187Thinking High (No Tools) | 91.3115 / 187Extended (no tools) | +2.99 |
| HLE | 51.4020 / 170Thinking High (With Tools) | 5316 / 170Extended (with tools, internet) | -1.60 |
| MMLU | 92.603 / 66Thinking High (No Tools) | 91.057 / 66Extended (no tools) | +1.55 |
| ARC-AGI-3 | 05 / 8Thinking High (No Tools) | 03 / 8最高（无工具） | — |
Agent Level Benchmark
Even 2/2| Benchmark | Gemini 3.1 Pro Preview | Claude Opus 4.6 | Diff |
|---|---|---|---|
| τ²-Bench | 90.802 / 43Thinking High (With Tools) | 91.891 / 43Extended (with tools) | -1.09 |
| τ²-Bench - Telecom | 99.301 / 35Thinking High (With Tools) | 99.252 / 35Extended (with tools) | +0.05 |
AI Agent - Tool Usage
Gemini 3.1 Pro Preview 2/2| Benchmark | Gemini 3.1 Pro Preview | Claude Opus 4.6 | Diff |
|---|---|---|---|
| Terminal Bench 2.0 | 68.508 / 47Thinking High (With Tools) | 65.4011 / 47Extended (with tools) | +3.10 |
| MCP-Atlas | 78.209 / 27Thinking High (With Tools) | 76.8010 / 27Deep Thinking (With Tools) | +1.40 |
Coding and Software Engineer
Even 2/2| Benchmark | Gemini 3.1 Pro Preview | Claude Opus 4.6 | Diff |
|---|---|---|---|
| LiveCodeBench | 91.703 / 123Thinking High (With Tools) | 7638 / 123Extended (no tools) | +15.70 |
| SWE-bench Verified | 80.6010 / 111Thinking High (With Tools) | 80.849 / 111Extended (with tools) | -0.24 |
Math and Reasoning
Claude Opus 4.6 2/2| Benchmark | Gemini 3.1 Pro Preview | Claude Opus 4.6 | Diff |
|---|---|---|---|
| FrontierMath - Tier 4 | 16.7020 / 80Normal (No Tools) | 22.9012 / 80最高（无工具） | -6.20 |
| FrontierMath | 36.9011 / 60Thinking High (No Tools) | 40.707 / 60最高（无工具） | -3.80 |
AI Agent - Information Search
Gemini 3.1 Pro Preview 1/1| Benchmark | Gemini 3.1 Pro Preview | Claude Opus 4.6 | Diff |
|---|---|---|---|
| BrowseComp | 85.904 / 52Thinking High (With Tools + Internet) | 8410 / 52Thinking (With Tools + Internet) | +1.90 |
Claw-style Agent Evaluation
Claude Opus 4.6 1/1| Benchmark | Gemini 3.1 Pro Preview | Claude Opus 4.6 | Diff |
|---|---|---|---|
| Pinch Bench | 86.7010 / 37Thinking (With Tools) | 87.407 / 37Thinking (With Tools) | -0.70 |
Commonsense Reasoning
Gemini 3.1 Pro Preview 1/1| Benchmark | Gemini 3.1 Pro Preview | Claude Opus 4.6 | Diff |
|---|---|---|---|
| Simple Bench | 79.602 / 63Normal (No Tools) | 67.608 / 63Normal (No Tools) | +12 |
Multimodal Understanding
Gemini 3.1 Pro Preview 1/1| Benchmark | Gemini 3.1 Pro Preview | Claude Opus 4.6 | Diff |
|---|---|---|---|
| MMMU | 80.5012 / 29Thinking High (No Tools) | 77.3016 / 29Extended (with tools) | +3.20 |
Specs
| Field | Gemini 3.1 Pro Preview | Claude Opus 4.6 |
|---|---|---|
| Publisher | Google Deep Mind | Anthropic |
| Release date | 2026-02-20 | 2026-02-05 |
| Model type | Multimodal model | Reasoning model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 1M | 1000K |
| Max output | 64K | 64K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Gemini 3.1 Pro Preview | Claude Opus 4.6 |
|---|---|---|
| Text input | $2 / 1M tokens | $0.5 / 1M tokens |
| Text output | $12 / 1M tokens | $25 / 1M tokens |
| Cache read | Not public | $0.5 / 1M tokens |
| Cache write | Not public | $10 / 1M tokens |
Summary
- Gemini 3.1 Pro Previewleads in:General Knowledge (4/6), AI Agent - Tool Usage (2/2), AI Agent - Information Search (1/1), Commonsense Reasoning (1/1), Multimodal Understanding (1/1)
- Claude Opus 4.6leads in:Math and Reasoning (2/2), Claw-style Agent Evaluation (1/1)
- Tied in:Agent Level Benchmark, Coding and Software Engineer
On average across the 18 shared benchmarks, Gemini 3.1 Pro Preview scores 2.37 higher.
Largest single-benchmark gap: LiveCodeBench — Gemini 3.1 Pro Preview 91.70 vs Claude Opus 4.6 76 (+15.70).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.