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 +11.5 / Relative gap: none clear
Relative edge: none clear / Relative gap: 数学推理 -11.5
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
Claude Opus 4.6 · 190.94
Best single
Claude Opus 4.6 · GDPval-AA 1606.00
Modality coverage
Claude Opus 4.6 · 2 modalities
Head to head
13
Benchmarks
12
Wins
1
Losses
+123.30
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.
13 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Claude Opus 4.6 | Claude Sonnet 4.6 |
|---|---|---|
ARC-AGI-2 综合评估 | 66.30Extended Thinking | 58.30Thinking Enabled |
GPQA Diamond 综合评估 | 91.31Extended Thinking | 89.90Thinking Enabled |
HLE 综合评估 | 53.00Extended Thinking ｜ Tools | 49.00Thinking Enabled ｜ Tools |
LiveBench 综合评估 | 76.33Thinking Level · High | 75.47Thinking Level · Medium |
SWE-bench Verified 编程与软件工程 | 80.84Extended Thinking ｜ Tools | 79.60Thinking Enabled |
22.90Thinking Level · High | 8.3016K | |
τ²-Bench - Telecom Agent能力评测 | 99.25Extended Thinking ｜ Tools | 97.90Thinking Enabled ｜ Tools |
BrowseComp AI Agent - 信息收集 | 84.00Thinking Enabled ｜ Tools | 74.70Thinking Enabled ｜ Tools |
MCP-Atlas AI Agent - 工具使用 | 76.80Deep Thinking Mode ｜ Tools | 69.50Standard Mode ｜ Tools |
OSWorld-Verified AI Agent - 工具使用 | 72.70Extended Thinking ｜ Tools | 72.50Thinking Enabled ｜ Tools |
Terminal Bench 2.0 AI Agent - 工具使用 | 65.40Extended Thinking ｜ Tools | 59.10Thinking Enabled ｜ Tools |
GDPval-AA 生产力知识 | 1606.00Extended Thinking ｜ Tools | 57.00Thinking Enabled |
Pinch Bench OpenClaw智能体能力综合测评 | 87.40Thinking Enabled ｜ Tools | 88.00Thinking Enabled ｜ Tools |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Claude Opus 4.6Anthropic | Claude Sonnet 4.6Anthropic |
|---|---|---|
Core specsRelease | 2026-02-05 | 2026-02-17 |
Context length | 1000K | 1M |
Max output | 65536 | 8192 |
MoE | No | No |
Supported modes | No mode data | 常规模式（Non-Thinking Mode）思考模式（Thinking Mode） |
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 | / | / |
ResourcesPaper / report | Introducing Claude Opus 4.6 | Introducing Claude Sonnet 4.6 |
Claude Sonnet 4.6
Anthropic
