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 Sonnet 4.5
Anthropic
Each axis is a category average, normalized to a 100-point radar.
Relative edge: AI Agent - 工具使用 +33.4 / Relative gap: none clear
Relative edge: none clear / Relative gap: AI Agent - 工具使用 -33.4
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
Claude Sonnet 4.5 · 62.62
Best single
Claude Sonnet 4.5 · AIME2025 100.00
Modality coverage
Claude Sonnet 4.5 · 2 modalities
Head to head
13
Benchmarks
13
Wins
0
Losses
+17.52
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 Sonnet 4.5 | Claude Sonnet 3.7 |
|---|---|---|
GPQA Diamond 综合评估 | 83.40Thinking Enabled | 77.00Thinking Enabled |
HLE 综合评估 | 33.60Thinking Enabled ｜ Tools | 10.30Thinking Enabled |
LiveBench 综合评估 | 78.26Thinking Enabled | 68.64Thinking Enabled |
SWE-bench Verified 编程与软件工程 | 77.20Thinking Enabled ｜ Tools | 70.30Thinking Enabled ｜ Tools |
AIME2025 数学推理 | 100.00Thinking Enabled ｜ Tools | 54.80Standard Mode |
FrontierMath 数学推理 | 5.20Standard Mode | 4.10Thinking Enabled |
OSWorld-Verified AI Agent - 工具使用 | 61.40Thinking Enabled ｜ Tools | 28.00Thinking Enabled ｜ Tools |
Simple Bench 常识推理 | 54.30Standard Mode | 46.40Thinking Enabled |
Terminal Bench Hard Agent能力评测 | 33.00Thinking Enabled ｜ Tools | 21.00Thinking Enabled ｜ Tools |
τ²-Bench Agent能力评测 | 84.70Thinking Enabled ｜ Tools | 61.80Thinking Enabled ｜ Tools |
τ²-Bench - Telecom Agent能力评测 | 98.00Thinking Enabled ｜ Tools | 55.00Thinking Enabled ｜ Tools |
GDPval-AA 生产力知识 | 39.00Thinking Enabled | 28.00Thinking Enabled |
AA-LCR 长上下文能力 | 66.00Thinking Enabled | 61.00Thinking Enabled |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Claude Sonnet 4.5Anthropic | Claude Sonnet 3.7Anthropic |
|---|---|---|
Core specsRelease | 2025-09-30 | 2025-02-25 |
Context length | 1000K | 128K |
Max output | 65536 | Not provided |
MoE | No | No |
Supported modes | 常规模式（Non-Thinking Mode）思考模式（Thinking Mode）深度思考（Deeper Thinking Mode） | No mode data |
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 | / | Not provided |
Image Input/Output | / | Not provided |
ResourcesPaper / report | Introducing Claude Sonnet 4.5 | Claude 3.7 Sonnet and Claude Code |
DataLearner blog | 全球最强编程大模型升级：Anthropic发布Claude Sonnet 4.5！同时还有一波重磅工具更新：Claude Code支持保存状态等 | Anthropic发布Claude 3.7 Sonnet大模型，全球最强编程模型再次进步。业界第一个既支持标准输出也支持扩展思考推理双重模式的单一大模型，评测结果超DeepSeek R1，低于Grok3-Beta Reasoning，免费用户可用 |
