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。
GPT-5.1
OpenAI
Each axis is a category average, normalized to a 100-point radar.
Relative edge: 数学推理 +15.9 / Relative gap: 常识推理 -5.6
Relative edge: 常识推理 +5.6 / Relative gap: 数学推理 -15.9
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
GPT-5.1 · 53.77
Best single
GPT-5.1 · AIME2025 94.00
Modality coverage
GPT-5.1 · 2 modalities
Head to head
9
Benchmarks
8
Wins
1
Losses
+14.87
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.
9 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | GPT-5.1 | Claude Opus 4 |
|---|---|---|
ARC-AGI 综合评估 | 72.80Thinking Level · High | 35.70Standard Mode |
ARC-AGI-2 综合评估 | 17.60Thinking Level · High | 8.60Standard Mode |
GPQA Diamond 综合评估 | 88.10Thinking Enabled | 79.60Standard Mode |
HLE 综合评估 | 42.70Thinking Level · High ｜ Tools | 10.70Standard Mode |
SWE-bench Verified 编程与软件工程 | 76.30Thinking Level · High | 72.50Standard Mode |
AIME2025 数学推理 | 94.00Thinking Level · High | 75.50Standard Mode |
FrontierMath 数学推理 | 26.70Thinking Level · High ｜ Tools | 4.50Standard Mode |
12.50Thinking Level · High ｜ Tools | 4.20Thinking Enabled | |
Simple Bench 常识推理 | 53.20Thinking Level · High | 58.80Thinking Enabled |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | GPT-5.1OpenAI | Claude Opus 4Anthropic |
|---|---|---|
Core specsRelease | 2025-11-12 | 2025-05-23 |
Context length | 400K | 200K |
Max output | 131072 | 32000 |
MoE | No | No |
Supported modes | 常规模式（Non-Thinking Mode）思考模式（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 | / | / |
Image Input/Output | / | / |
ResourcesPaper / report | GPT-5.1: A smarter, more conversational ChatGPT | Introducing Claude 4 |
DataLearner blog | OpenAI发布GPT-5.1：围绕“对话体验、一致性、任务适配性”进行的系统化优化的小幅更新！ | Anthropic发布Claude4，全球最强编程大模型，大幅提升AI Agent系统所需的各项能力，最长可以7小时连续工作，80%工程任务自主完成 |
Claude Opus 4
Anthropic
