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。
Opus 4.7
Anthropic
Claude Opus 4.8
Anthropic
Each axis is a category average, normalized to a 100-point radar.
Relative edge: none clear / Relative gap: 数学推理 -17.1
Relative edge: 数学推理 +17.1 / Relative gap: none clear
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 4.8 · 181.84
Best single
Opus 4.7 · Text Arena (Coding) 1562.39
Modality coverage
Opus 4.7 · 2 modalities
Head to head
14
Benchmarks
2
Wins
12
Losses
-4.17
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.
14 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Opus 4.7 | Claude Opus 4.8 |
|---|---|---|
HLE 综合评估 | 54.70Extended Thinking ｜ Tools | 57.90Extended Thinking ｜ Tools |
LiveBench 综合评估 | 76.91Deep Thinking Mode | 78.79Deep Thinking Mode |
GPQA Diamond 科学与综合推理 | 94.20Extended Thinking | 93.60Thinking Level · High |
SWE-Bench Pro - Public 编程与软件工程 | 64.30Extended Thinking ｜ Tools | 69.20Extended Thinking ｜ Tools |
SWE-bench Verified 编程与软件工程 | 87.60Extended Thinking ｜ Tools | 88.60Extended Thinking ｜ Tools |
Text Arena (Coding) 编程与软件工程 | 1562.39Standard Mode | 1545.05Standard Mode |
WeirdML v2 编程与软件工程 | 76.40Standard Mode ｜ Tools | 82.89Thinking Level · Extra High ｜ Tools |
SimpleBench 常识推理 | 62.90Standard Mode | 64.80Standard Mode |
31.71Thinking Level · High | 56.10Thinking Level · High | |
FrontierMath v2 数学推理 | 70.18Thinking Level · High | 80.00Thinking Level · High |
BrowseComp AI Agent - 信息收集 | 79.30Extended Thinking ｜ Tools | 84.30Thinking Level · High ｜ Tools |
MCP-Atlas AI Agent - 工具使用 | 79.10Thinking Level · High ｜ Tools | 82.20Thinking Level · High ｜ Tools |
OSWorld-Verified AI Agent - 工具使用 | 78.00Extended Thinking ｜ Tools | 83.40Extended Thinking ｜ Tools |
Terminal-Bench 2.1 AI Agent - 工具使用 | 69.70Thinking Level · High ｜ Tools | 78.90Thinking Level · High ｜ Tools |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Opus 4.7Anthropic | Claude Opus 4.8Anthropic |
|---|---|---|
Core specsRelease | 2026-04-16 | 2026-05-28 |
Context length | 1000K | 1M |
Max output | 131072 | 128000 |
MoE | No | No |
LicenseCode Open Source | Closed Source | Closed Source |
Weights Open Source | Closed Source | Closed Source |
Commercial use | 不开源 | 不开源 |
Modality supportText Input/Output | / | / |
Image Input/Output | / | / |
ResourcesPaper / report | Introducing Claude Opus 4.7 | Introducing Claude Opus 4.8 |
DataLearner blog | Anthropic发布Claude Opus 4.7：编程能力大幅跃升，视觉分辨率提升超3倍，首个搭载网络安全防护机制的旗舰模型！ | Anthropic发布Claude Opus 4.8：定价不变，编程与智能体能力小幅提升， |
