GPT-5
OpenAI·4 个数据来源·更新于 2026-11-10
评测表现
只在同一来源、同一口径下比较。切换来源可查看不同测试结果。
不同来源的分数不能直接相加或横向比较;评测任务成本不是 API Token 单价。
逐项基准成绩
34 项已收录成绩 · 保留原始单位和测试条件
Thinking mode enabled (up to 128K tokens) with step-by-step reasoning and multi-language code understanding.
成绩出处GPT-5 standard with thinking mode enabled (no tools) - competition mathematics.
成绩出处GPT-5 with thinking mode enabled - Agentic search & browsing benchmark.
成绩出处GPT-5 with thinking mode - Scientific figure reasoning and interpretation.
成绩出处GPT-5 with thinking mode enabled - Instruction-following in freeform writing.
成绩出处Thinking mode enabled for factual accuracy assessment. Measured hallucination rate on open-source prompts.
成绩出处GPT-5 standard with thinking mode enabled (with python tool only) - FrontierMath Tier 1-3 expert-level mathematics.
成绩出处Thinking mode enabled for medical hallucination detection. Measured inaccuracies on challenging healthcare conversations.
成绩出处GPT-5 standard with thinking mode enabled (no tools) - Harvard-MIT Mathematics Tournament.
成绩出处GPT-5 standard with thinking mode (no tools) - Full set of expert-level questions across subjects.
成绩出处GPT-5 - Internal API instruction following evaluation (hard difficulty).
成绩出处Thinking mode enabled for hallucination detection. Measured on open-source prompts for concept-based factual queries.
成绩出处Thinking mode enabled for hallucination detection. Measured on open-source prompts for object-based factual queries.
成绩出处Thinking mode enabled with step-by-step mathematical problem solving and verification.
成绩出处Standard benchmark across multiple academic subjects with comprehensive knowledge evaluation.
成绩出处GPT-5 with thinking mode - College-level visual problem-solving with multimodal reasoning.
成绩出处GPT-5 with thinking mode - Graduate-level visual problem-solving with advanced multimodal reasoning.
成绩出处GPT-5 with thinking mode enabled - Multi-turn instruction following benchmark.
成绩出处Thinking mode enabled (up to 128K tokens) with enhanced reasoning capabilities and iterative problem-solving approach.
成绩出处GPT-5 - IC SWE Diamond Freelance Coding Tasks (earnings-based evaluation).
成绩出处GPT-5 with thinking mode - Function calling benchmark (retail domain).
成绩出处GPT-5 with thinking mode - Function calling benchmark (telecom domain).
成绩出处GPT-5 with thinking mode - Video-based multimodal reasoning (max frame 256).
成绩出处技术规格
只展示有可靠来源的资料;优先采用厂商官网与官方模型仓库。
- 发布日期
- 2025-08-07LLM Stats
- 知识截止
- 2024-09-30LLM Stats
- 上下文窗口
- 128K TokenBenchLM
- 最大输出
- 128K TokenOpenRouter
- 输入模态
- 文本、图像、文件OpenRouter
- 输出模态
- 文本OpenRouter
- 许可证
- ProprietaryLLM Stats
价格与用量
美元 / 百万 Token。不同服务商或测试配置的报价分别列出。
| 来源 / 服务商 | 输入 | 输出 | 缓存读取 |
|---|---|---|---|
| OpenRouter · openai/gpt-5 | $1.25 | $10 | $0.125 |
每个数字,都有出处
同名模型通过开发机构和明确版本关联。预览版、日期版本和不同规模模型分别建档。
LLM Stats
公开模型页与公开榜单;自报成绩单独标识
BenchLM
公开评测数据;保留来源原始口径
Arena
Arena 官方公开数据集 · CC BY 4.0
OpenRouter
公开模型目录与 API 报价
查看全部配置与采集记录
| 来源 / 配置 | 采集时间 | 原始数据 |
|---|---|---|
| LLM StatsGPT-5SHA-256 73b61dd067d6233b… | 2026-11-10T13:55:25Z | 查看来源 |
| BenchLMGPT-5 (medium) | 2026-11-10 | 查看来源 |
| ArenaGPT-5 (High) | 2026-11-10T14:07:52Z | 查看来源 |
| ArenaGPT-5 (Medium) | 2026-11-10T14:07:52Z | 查看来源 |
| ArenaGPT-5 (High) | 2026-11-10T14:07:52Z | 查看来源 |
| OpenRouterGPT-5SHA-256 63cbc45064d84060… | 2026-11-10T13:51:49Z | 查看来源 |