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
Each axis is a category average, normalized to a 100-point radar.
Relative edge: 编程与软件工程 +9.2 / Relative gap: 常识推理 -13.8
Relative edge: 常识推理 +13.8 / Relative gap: 编程与软件工程 -9.2
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
Opus 4.7 · 68.86
Best single
Opus 4.7 · GPQA Diamond 94.20
Modality coverage
Gemini 3.5 Flash · 4 modalities
Head to head
11
Benchmarks
7
Wins
4
Losses
+1.61
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.
11 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Opus 4.7 | Gemini 3.5 Flash |
|---|---|---|
ARC-AGI-2 综合评估 | 75.80Thinking Level · High | 72.10Thinking Level · High | Tools |
HLE 综合评估 | 54.70Extended Thinking | Tools | 40.20Thinking Level · High | Tools |
LiveBench 综合评估 | 76.91Deep Thinking Mode | 75.02Thinking Level · High |
GPQA Diamond 科学与综合推理 | 94.20Extended Thinking | 92.80Thinking Level · High |
SWE-Bench Pro - Public 编程与软件工程 | 64.30Extended Thinking | Tools | 55.10Thinking Level · High | Tools |
SimpleBench 常识推理 | 62.90Standard Mode | 76.70Standard Mode |
31.71Thinking Level · High | 26.83Thinking Level · High | |
FrontierMath v2 数学推理 | 70.18Thinking Level · High | 62.81Thinking Level · High |
MCP-Atlas AI Agent - 工具使用 | 79.10Thinking Level · High | Tools | 83.60Thinking Level · High | Tools |
OSWorld-Verified AI Agent - 工具使用 | 78.00Extended Thinking | Tools | 78.40Thinking Level · High | Tools |
Terminal-Bench 2.1 AI Agent - 工具使用 | 69.70Thinking Level · High | Tools | 76.20Thinking Level · High | Tools |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Opus 4.7Anthropic | Gemini 3.5 FlashGoogle Deep Mind |
|---|---|---|
Core specsRelease | 2026-04-16 | 2026-06-20 |
Context length | 1000K | 1M |
Max output | 131072 | 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 4.7 | Gemini 3.5: frontier intelligence with action |
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! | Not provided |

Gemini 3.5 Flash
Google Deep Mind