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 4.8
Anthropic
Gemini 3.1 Pro Preview
Google Deep Mind
Each axis is a category average, normalized to a 100-point radar.
Relative edge: 编程与软件工程 +14.9 / Relative gap: 常识推理 -14.8
Relative edge: 常识推理 +14.8 / Relative gap: 编程与软件工程 -14.9
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 · 189.89
Best single
Claude Opus 4.8 · Text Arena (Coding) 1545.05
Modality coverage
Gemini 3.1 Pro Preview · 4 modalities
Head to head
13
Benchmarks
9
Wins
4
Losses
+12.99
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 4.8 | Gemini 3.1 Pro Preview |
|---|---|---|
HLE 综合评估 | 57.90Extended Thinking ｜ Tools | 51.40Thinking Level · High ｜ Tools |
LiveBench 综合评估 | 78.79Deep Thinking Mode | 79.93Thinking Level · High |
GPQA Diamond 科学与综合推理 | 93.60Thinking Level · High | 94.30Thinking Level · High |
DeepSWE 编程与软件工程 | 59.00Deep Thinking Mode ｜ Tools | 12.00Thinking Level · High ｜ Tools |
SWE-Bench Pro - Public 编程与软件工程 | 69.20Extended Thinking ｜ Tools | 54.20Thinking Level · High ｜ Tools |
SWE-bench Verified 编程与软件工程 | 88.60Extended Thinking ｜ Tools | 80.60Thinking Level · High ｜ Tools |
Text Arena (Coding) 编程与软件工程 | 1545.05Standard Mode | 1461.49Standard Mode |
WeirdML v2 编程与软件工程 | 82.89Thinking Level · Extra High ｜ Tools | 72.10Standard Mode ｜ Tools |
SimpleBench 常识推理 | 64.80Standard Mode | 79.60Standard Mode |
BrowseComp AI Agent - 信息收集 | 84.30Thinking Level · High ｜ Tools | 85.90Thinking Level · High ｜ Tools |
MCP-Atlas AI Agent - 工具使用 | 82.20Thinking Level · High ｜ Tools | 78.20Thinking Level · High ｜ Tools |
OSWorld-Verified AI Agent - 工具使用 | 83.40Extended Thinking ｜ Tools | 76.20Thinking Enabled ｜ Tools |
Terminal-Bench 2.1 AI Agent - 工具使用 | 78.90Thinking Level · High ｜ Tools | 73.80Thinking Level · High ｜ Tools |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Claude Opus 4.8Anthropic | Gemini 3.1 Pro PreviewGoogle Deep Mind |
|---|---|---|
Core specsRelease | 2026-05-28 | 2026-02-20 |
Context length | 1M | 1M |
Max output | 128000 | 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 4.8 | Gemini 3.1 Pro: A smarter model for your most complex tasks |
DataLearner blog | Anthropic发布Claude Opus 4.8：定价不变，编程与智能体能力小幅提升， | Not provided |
