Gemini 3.1 Pro PreviewvsClaude Opus 4.6
Across 15 shared benchmarks, Gemini 3.1 Pro Preview leads overall: Gemini 3.1 Pro Preview wins 8, Claude Opus 4.6 wins 6, with 1 ties and an average score difference of +1.71.
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 Preview8 wins(53%)Ties1(40%)6 winsClaude Opus 4.6
Benchmark scores
Grouped by capability, sorted by largest gap within each. 15 shared benchmarks.
General Knowledge
Gemini 3.1 Pro Preview 3/5| Benchmark | Gemini 3.1 Pro Preview | Claude Opus 4.6 | Diff |
|---|---|---|---|
| ARC-AGI-2 | 77.107 / 59Thinking High (No Tools) | 66.3015 / 59Extended (no tools) | +10.80 |
| GPQA Diamond | 94.303 / 178Thinking High (No Tools) | 91.3114 / 178Extended (no tools) | +2.99 |
| HLE | 51.4015 / 157Thinking High (With Tools) | 5311 / 157Extended (with tools, internet) | -1.60 |
| MMLU | 92.603 / 65Thinking High (No Tools) | 91.057 / 65Extended (no tools) | +1.55 |
| ARC-AGI-3 | 03 / 6Thinking High (No Tools) | 01 / 6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 / 40Thinking High (With Tools) | 91.891 / 40Extended (with tools) | -1.09 |
| τ²-Bench - Telecom | 99.301 / 35Thinking High (With Tools) | 99.252 / 35Extended (with tools) | +0.05 |
Coding and Software Engineer
Even 2/2| Benchmark | Gemini 3.1 Pro Preview | Claude Opus 4.6 | Diff |
|---|---|---|---|
| LiveCodeBench | 91.703 / 120Thinking High (With Tools) | 7637 / 120Extended (no tools) | +15.70 |
| SWE-bench Verified | 80.6010 / 108Thinking High (With Tools) | 80.849 / 108Extended (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 | 85.903 / 45Thinking High (With Tools + Internet) | 847 / 45Thinking (With Tools + Internet) | +1.90 |
AI Agent - Tool Usage
Gemini 3.1 Pro Preview 1/1| Benchmark | Gemini 3.1 Pro Preview | Claude Opus 4.6 | Diff |
|---|---|---|---|
| Terminal Bench 2.0 | 68.508 / 46Thinking High (With Tools) | 65.4011 / 46Extended (with tools) | +3.10 |
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 |
Multimodal Understanding
Gemini 3.1 Pro Preview 1/1| Benchmark | Gemini 3.1 Pro Preview | Claude Opus 4.6 | Diff |
|---|---|---|---|
| MMMU | 80.5011 / 28Thinking High (No Tools) | 77.3015 / 28Extended (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 | 32K | 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 (3/5), AI Agent - Information Search (1/1), AI Agent - Tool Usage (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 15 shared benchmarks, Gemini 3.1 Pro Preview scores 1.71 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.