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
OpenAI
Each axis is a category average, normalized to a 100-point radar.
Relative edge: 常识推理 +3.5 / Relative gap: 编程与软件工程 -9.0
Relative edge: 编程与软件工程 +9.0 / Relative gap: 常识推理 -3.5
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 · 58.96
Best single
GPT-5 · AIME2025 99.60
Modality coverage
GPT-5 · 2 modalities
Head to head
13
Benchmarks
4
Wins
8
Losses
-2.18
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 | GPT-5 | GPT-5.1 |
|---|---|---|
ARC-AGI 综合评估 | 65.70Thinking Level · High | 72.80Thinking Level · High |
ARC-AGI-2 综合评估 | 9.90Thinking Level · High | 17.60Thinking Level · High |
GPQA Diamond 综合评估 | 87.30Thinking Enabled ｜ Tools | 88.10Thinking Enabled |
HLE 综合评估 | 35.20Thinking Enabled ｜ Tools | 42.70Thinking Level · High ｜ Tools |
SWE-Bench Pro - Public 编程与软件工程 | 36.30Thinking Level · High | 50.80Thinking Level · High |
SWE-bench Verified 编程与软件工程 | 72.80Thinking Level · High | 76.30Thinking Level · High |
AIME2025 数学推理 | 99.60Thinking Enabled ｜ Tools | 94.00Thinking Level · High |
FrontierMath 数学推理 | 26.30Thinking Level · High ｜ Tools | 26.70Thinking Level · High ｜ Tools |
12.50Thinking Level · High | 12.50Thinking Level · High ｜ Tools | |
MMMU 多模态理解 | 84.20Thinking Level · High | 85.40Thinking Level · High |
Simple Bench 常识推理 | 56.70Thinking Level · High | 53.20Thinking Level · High |
τ²-Bench - Telecom Agent能力评测 | 96.70Thinking Level · High ｜ Tools | 95.60Thinking Level · High ｜ Tools |
BrowseComp AI Agent - 信息收集 | 54.90Thinking Enabled ｜ Tools | 50.80Thinking Level · High |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | GPT-5OpenAI | GPT-5.1OpenAI |
|---|---|---|
Core specsRelease | 2025-08-07 | 2025-11-12 |
Context length | 400K | 400K |
Max output | 131072 | 131072 |
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） | 常规模式（Non-Thinking Mode）思考模式（Thinking Mode） |
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 | Introducing GPT-5 | GPT-5.1: A smarter, more conversational ChatGPT |
DataLearner blog | OpenAI发布GPT-5：这是一个包含实时路由的AI系统，而不仅仅是一个模型 | 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！ |
GPT-5.1
OpenAI
