Skip to content

Perplexity Shares GPT-6.2 Astra and Sol WANDR Evals

Aravind Srinivas · XRelayed· @AravSrinivas·· 9 hours agoPicks

1.2K views · 4 likes · 0 reposts (at collection)

Original

What happened

Perplexity says GPT-6.2 Astra and GPT-6.2 Sol are available in Perplexity Search and Computer. On its WANDR benchmark, Astra scored 0.783 at about $12.54 per task, up 0.095 from GPT-6 Astra; Sol scored 0.746 at about $2.65, up 0.065 from GPT-6.1 Sol. Aravind Srinivas reposted the results and noted improvements in wide-and-deep research performance.

Why it matters

On Perplexity’s WANDR benchmark, GPT-6.2 Astra and Sol score higher than their cited predecessors, with Astra costing more per task than Sol.

Article

Astra and Sol 6.2 evals on Perplexity. Good improvements on Wide-and-Deep-Research performance

Quoted postPerplexity@perplexity_ai

GPT-6.2 Astra and GPT-6.2 Sol are now available in Perplexity Search and Computer.

On our WANDR benchmark, GPT-6.2 Astra scored 0.783 at about $12.54 per task, up 0.095 from GPT-6 Astra.

GPT-6.2 Sol hit 0.746 at about $2.65, up 0.065 from GPT-6.1 Sol.

View the quoted post on X

Reported by 2 sources

    The story so far

    OpenAI released the GPT-6.2 Astra and Sol models, which are available now in ChatGPT Work, Codex, and the API. Astra, positioned as the company’s new flagship model, offers reduced pricing with API rates 20% lower than its predecessor at $8 per million input tokens and $40 per million output tokens, while Sol maintains the existing $2 and $10 pricing structure. OpenAI also expanded access to its Ultrafast mode to include Pro 200 and Pro 500 subscription tiers. The company reports that GPT-6.2 Astra sets new highs on benchmarks including Agents' Last Exam, BenchCAD 2.1, and Terminal-Bench Science 0.1 at lower task costs. However, external evaluations show mixed results. Epoch AI reported that GPT-6.2 Astra scored 65% on internal automation quality standards, trailing Fable 5.2. Additionally, independent testing by Simon Willison indicated that the model struggled with animation tasks compared to other frontier models. OpenAI also implemented tighter cybersecurity safeguards for the new models and plans to provide access through its Daybreak platform for approved defenders, though the company noted that these safeguards may increase refusal rates for some security research tasks.

    How the story developed · 3

    View full event
    1. 11/18 06:15 (UTC+8)
      Tibor Blaho Tests GPT-6.2 Astra and Sol on Daily WorkTibor Blaho · X
    2. 11/18 06:15 (UTC+8)

      Perplexity Shares GPT-6.2 Astra and Sol WANDR Evals This report

    3. 11/18 02:36 (UTC+8)
      OpenAI Introduces GPT-6.2 Astra and SolOpenAI News

    Read next

    See the full storyOpenAI Launches GPT-6.2 Astra and Sol with Reduced API Pricing and Expanded Availability
    This story is in 11/18 AI DailyRead the whole issue