See key specs and per-benchmark scores for each model/mode. Scroll horizontally for all columns. 当前对比 2 个模型的评测数据与核心参数。
Claude Opus 4.6
Anthropic
Each axis is a category average, normalized to a 100-point radar.
Relative edge: 数学推理 +3.4 / Relative gap: 编程与软件工程 -7.7
Relative edge: 编程与软件工程 +7.7 / Relative gap: 数学推理 -3.4
Method: for each model and benchmark, the chart first averages all scores in the current mode scope instead of taking the best score, then averages those benchmark scores within each category. Only benchmarks with at least two selected models scored are included; missing values are not counted as zero.
Best overall
Gemini 3.1 Pro Preview · 75.94
Best single
Gemini 3.1 Pro Preview · τ²-Bench - Telecom 99.30
Modality coverage
Gemini 3.1 Pro Preview · 4 modalities
Head to head
18
Benchmarks
6
Wins
12
Losses
-2.56
Average diff
Compare benchmark results across thinking modes and tool usage.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Complete scores for each model/mode across selected benchmarks.
18 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Claude Opus 4.6 | Gemini 3.1 Pro Preview |
|---|---|---|
ARC-AGI-2 综合评估 | 66.30Extended Thinking | 77.10Thinking Level · High |
GPQA Diamond 综合评估 | 91.31Extended Thinking | 94.30Thinking Level · High |
HLE 综合评估 | 53.00Extended Thinking ｜ Tools | 51.40Thinking Level · High ｜ Tools |
LiveBench 综合评估 | 76.33Thinking Level · High | 79.93Thinking Level · High |
MMLU 综合评估 | 91.05Extended Thinking | 92.60Thinking Level · High |
LiveCodeBench 编程与软件工程 | 76.00Extended Thinking | 91.70Thinking Level · High ｜ Tools |
SWE-bench Verified 编程与软件工程 | 80.84Extended Thinking ｜ Tools | 80.60Thinking Level · High ｜ Tools |
FrontierMath 数学推理 | 40.70Thinking Level · High | 36.90Thinking Level · High |
22.90Thinking Level · High | 16.70Standard Mode | |
MMMU 多模态理解 | 77.30Extended Thinking ｜ Tools | 80.50Thinking Level · High |
Simple Bench 常识推理 | 67.60Standard Mode | 79.60Standard Mode |
τ²-Bench Agent能力评测 | 91.89Extended Thinking ｜ Tools | 90.80Thinking Level · High ｜ Tools |
τ²-Bench - Telecom Agent能力评测 | 99.25Extended Thinking ｜ Tools | 99.30Thinking Level · High ｜ Tools |
BrowseComp AI Agent - 信息收集 | 84.00Thinking Enabled ｜ Tools | 85.90Thinking Level · High ｜ Tools |
MCP-Atlas AI Agent - 工具使用 | 76.80Deep Thinking Mode ｜ Tools | 78.20Thinking Level · High ｜ Tools |
OSWorld-Verified AI Agent - 工具使用 | 72.70Extended Thinking ｜ Tools | 76.20Thinking Enabled ｜ Tools |
Terminal Bench 2.0 AI Agent - 工具使用 | 65.40Extended Thinking ｜ Tools | 68.50Thinking Level · High ｜ Tools |
Pinch Bench OpenClaw智能体能力综合测评 | 87.40Thinking Enabled ｜ Tools | 86.70Thinking Enabled ｜ Tools |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Claude Opus 4.6Anthropic | Gemini 3.1 Pro PreviewGoogle Deep Mind |
|---|---|---|
Core specsRelease | 2026-02-05 | 2026-02-20 |
Context length | 1000K | 1M |
Max output | 65536 | 65536 |
MoE | No | No |
LicenseCode Open Source | Not provided | Not provided |
Weights Open Source | Not provided | Not provided |
Commercial use | 不开源 | 不开源 |
Modality supportText Input/Output | / | / |
Image Input/Output | / | / |
Audio Input/Output | Not provided | / |
Video Input/Output | Not provided | / |
ResourcesPaper / report | Introducing Claude Opus 4.6 | Gemini 3.1 Pro: A smarter model for your most complex tasks |
Gemini 3.1 Pro Preview
Google Deep Mind
