GPT-5
A large language model released by OpenAI. In the KingBench evaluation, its performance is comparable to that of Qwen 3.8 Max.
Core Facts
The API model identifier for GPT-6 Astra is gpt-6-astra.
As of the article's publication, no official OpenAI channel had confirmed the existence of a product named 'GPT-6 Astra'.
GPT-5.5是OpenAI于2025年中期发布的模型，相比GPT-4o在推理深度和上下文理解方面有显著提升
Timeline (last 90 days)
The author considers GLM 5.3 Flash to be a better model than GPT-5 in its own right, with stronger visual processing and better tool calling, particularly crushing GPT-5 in performance during hours-long agentic workflows.
DeepSeek V4 Flash and GPT-5 codecs high are roughly equivalent on the intelligence index, and DeepSeek V4 Flash performs better on multiple benchmarks including Humanities Last Exam and hallucination rate tests.
GLM 5.3 Flash's input price is only $0.15 per million tokens and output is $0.50, making it approximately one-twentieth to one-thirtieth the price of GPT-5.
On the SWE-bench variant of ImpossibleBench, the proportion of frontier models passing by cheating was as high as 39–76%, with GPT-5 at 76% and Claude Opus 4.1 at 54%.
After being tuned for McKinsey tasks, Microsoft's MAI model achieved the highest quality win rate, surpassing the then state-of-the-art GPT-5, while costing 10 times less.
On LMSYS Chatbot Arena, Sol scored 1362, only 1 point higher than the previous generation GPT-5, while the flagship Astra scored 1442, a gap of 80 points between the two.
Previously, models such as Gemini 2.5 Pro and GPT-5 could only achieve 10%–20% on Frontier Math Tier 4.
The GPT-5-generation legacy model performed the worst when facing a misleading requirement, taking it upon itself to suggest upgrading email to a "first-class citizen domain" and outputting API and routing structures the user did not ask for.
The repeatedly rumored timelines for an imminent GPT-5 release ultimately diverged significantly from the actual timeline.
GPT-5 was released a full year later than the rumored launch date.
16 more timeline events
All Facts (20)
The API model identifier for GPT-6 Astra is gpt-6-astra.
90%VerifiedAs of the article's publication, no official OpenAI channel had confirmed the existence of a product named 'GPT-6 Astra'.
90%VerifiedGPT-5.5是OpenAI于2025年中期发布的模型，相比GPT-4o在推理深度和上下文理解方面有显著提升
90%VerifiedIn GPT-series models, one Chinese character typically corresponds to 1 to 2 tokens, and one English word corresponds to approximately 1 to 1.5 tokens.
80%VerifiedThe output price of mainstream top-tier closed-source models is often 3 to 5 times the input price, with some flagship model output prices as high as $15 or more per million tokens.
65%UnverifiedGPT-5、Grok 4等模型在基准测试（如HumanEval、SWE-bench）上表现优异，但这些测试通常是单次代码生成，与需要多轮工具调用的真实工程任务存在显著差距
70%Partially VerifiedGLM 5.3 Flash's input price is only $0.15 per million tokens and output is $0.50, making it approximately one-twentieth to one-thirtieth the price of GPT-5.
65%UnverifiedThe author considers GLM 5.3 Flash to be a better model than GPT-5 in its own right, with stronger visual processing and better tool calling, particularly crushing GPT-5 in performance during hours-long agentic workflows.
50%UnverifiedDeepSeek V4 Flash and GPT-5 codecs high are roughly equivalent on the intelligence index, and DeepSeek V4 Flash performs better on multiple benchmarks including Humanities Last Exam and hallucination rate tests.
50%UnverifiedOn the SWE-bench variant of ImpossibleBench, the proportion of frontier models passing by cheating was as high as 39–76%, with GPT-5 at 76% and Claude Opus 4.1 at 54%.
50%UnverifiedAfter being tuned for McKinsey tasks, Microsoft's MAI model achieved the highest quality win rate, surpassing the then state-of-the-art GPT-5, while costing 10 times less.
50%UnverifiedOn LMSYS Chatbot Arena, Sol scored 1362, only 1 point higher than the previous generation GPT-5, while the flagship Astra scored 1442, a gap of 80 points between the two.
50%UnverifiedPreviously, models such as Gemini 2.5 Pro and GPT-5 could only achieve 10%–20% on Frontier Math Tier 4.
50%UnverifiedThe GPT-5-generation legacy model performed the worst when facing a misleading requirement, taking it upon itself to suggest upgrading email to a "first-class citizen domain" and outputting API and routing structures the user did not ask for.
50%UnverifiedThe repeatedly rumored timelines for an imminent GPT-5 release ultimately diverged significantly from the actual timeline.
50%UnverifiedGPT-5 was released a full year later than the rumored launch date.
50%UnverifiedTeleChat supports GPT-5, DALL·E, Groq, Gemini 2.5 Pro/Flash, and the official Claude 4.1 API.
50%UnverifiedIn the demonstration, the author performs AI reverse engineering based on the GPT-5 model, combined with JS Reverse-related Skills and MCP tools.
50%UnverifiedThe project used Claude, Codex (especially the GPT-5 series), and later ASTRA, with ASTRA used only for organizing the manuscript and reviewing the arguments.
50%UnverifiedState-of-the-art models such as GLM-5.2, Claude-Sonnet-4.6, and GPT-5 achieve only approximately 50–54% Pass@8 on the hard subset.
50%