Command Palette
Search for a command to run...

OpenAI's GPT-5.6 Sol Scores 88.8% on WeirdML, Tops CritPt and DeepSWE

aiai-modelingai-research-evalsai-model-releases 171 posts · 76 accounts

OpenAI's GPT-5.6 Sol scored 88.8% on the WeirdML benchmark, narrowly ahead of Claude Fable 5 at less than half the price. Separate benchmark updates on Thursday also showed Sol leading CritPt, a test of unpublished research-level physics problems, and topping the DeepSWE coding-agent leaderboard at 73%.

Artificial Analysis said Sol gained about 5 points over GPT-5.5 on CritPt and beat Claude Fable 5 by about 4 points. CritPt, developed by Argonne and the University of Illinois Urbana-Champaign, uses graduate-level physics problems contributed by more than 60 researchers from more than 30 institutions. DeepSWE measures performance on 113 software-engineering tasks across 91 repositories and five languages; one comparison put Sol at about 72% to 73% and $8.4 per task, versus around 70% and $13 to $22 for Fable 5. A separate comment said CritPt still appears close to a 30% ceiling, while the WeirdML result showed no run below 60% of the state-of-the-art score across 85 tests.

From the sources (25 posts)

@btibor91

OpenAI announced a new livestream called "ChatGPT Work - Our biggest update for work in ChatGPT" for tomorrow

@testingcatalog

OPENAI 🔥: A new ChatGPT Work livestream has been announced for tomorrow. > Tomorrow, we're introducing a new partner for your most ambitious work. That’s something 👀

@wesroth

OpenAI has announced a new ChatGPT Work livestream with the teaser: “We’re introducing a new partner for your most ambitious work.” 👀

@testingcatalog

OPENAI 🔥: ChatGPT Work will likely arrive in the form of an upgraded dedicated workspace, individual for every user. What we know so far 👀 > "ChatGPT Work can help you build websites, prototype new ideas, create presentations and documen

@financialjuice

OpenAI's Altman expects a smoother process working with the government on AI

@firstsquawk

OPENAI MADE 'MANY CHANGES' AFTER TALKING TO GOVT, ALTMAN SAYS

@financialjuice

OpenAI's Altman: OpenAI made many changes after talking to the government.

@financialjuice

OpenAI's Altman: OpenAI’s newest AI model is 54% more token-efficient on agentic coding.

@stockmktnewz

OpenAI CEO Sam Altman said that its latest AI model is 54% more token efficent on agent coding tasks - CNBC

@cnbc

OpenAI's newest AI model is 54% more token efficient on agentic coding, Altman tells CNBC

@business

Sam Altman said OpenAI made “many changes” during its discussions with the Trump administration before moving ahead with releasing its newest AI models to the general public

@polymarket

NEW: Sam Altman reveals OpenAI made “many changes” during talks with the Trump administration before GPT-5.6’s release.

@exec_sum

BREAKING: OpenAI is set to launch GPT-5.6, its most capable model yet after a delayed rollout

@daveaitel

RT @OpenAI: Today. 10am PT.

@firstsquawk

OPENAI UNVEILS THE GPT-5.6 MODEL FAMILY—SOL, TERRA, AND LUNA—WITH ROLLOUT ACROSS CHATGPT, CODEX, AND THE API.

@firstsquawk

OPENAI LAUNCHES CHATGPT WORK, POWERED BY GPT-5.6, WITH ROLLOUT BEGINNING FOR PRO, ENTERPRISE, AND EDU USERS, WHILE PLUS AND BUSINESS WILL FOLLOW.

@firstsquawk

OPENAI'S NEW CHATGPT DESKTOP APP, COMBINING CHAT, WORK, AND CODEX, IS ROLLING OUT GLOBALLY ON MAC AND WINDOWS FOR ALL USERS.

@sama

5.6 livestream going now. in addition to the model, 3 major product things. 1. ChatGPT Work--really big deal! 2. new ChatGPT desktop app 3. hosted sites

@digg

OpenAI said on its live stream that GPT-5.6 Sol, Terra and Luna are rolling out today. Sol is coming to paid plans over the next 24 hours. Terra and Luna are coming to free users.

@scaling01

GPT-5.6 Benchmarks

@wallstengine

OpenAI introduces ChatGPT Work, powered by GPT-5.6, and says Sol, Terra and Luna are rolling out across ChatGPT, Codex and the API.

@firstsquawk

OPENAI LAUNCHES GPT-5.6 FAMILY OF MODELS FOR GENERAL AVAILABILITY FOLLOWING LIMITED PREVIEW

@scaling01

GPT-5.6-Sol scoring a massive 7.78% on ARC-AGI-3 this is a massive jump over Opus 4.8's 1.5%

@cursor_ai

GPT-5.6 Sol, Terra, and Luna are now available in Cursor. On CursorBench, Sol scores 67.2%.

@sama

obviously the best model we have ever produced, but also one of the best blog posts we have ever produced:

Preview built on a synthetic news corpus (16 weeks, Apr–Jul 2026). Impact calls are model reads, not price data.

About Archive