Comments
Hacker News
Edit: It was pointed out to me that Opus 4.8 got "21%" for successfully fully completing ~1-in-5 tasks, but also got "55.7%" for obtaining significant partial credit on some of the ~4-in-5 tasks it could not fully complete.
---------------
Why does Anthropic say here that Opus 4.8 scored 55.7% on OSWorld 2.0 benchmark, but the paper published by the authors of OSWorld 2.0 say they achieved a benchmark of ~21% with Opus 4.8? [0]
That's a huge gap, considering that the paper was published just 2-4 weeks ago.
I understand that the benchmark authors have an incentive to publish lower numbers (to show that the benchmark has potential longevity) and that Anthropic has incentive to publish higher numbers, but the other models seem pretty inflated as well. The benchmark authors shows GPT-5.5 at 14%, and Anthropic shows GPT-5.6 Sol at 62.6%.
Is there any reasonable explanation for this? Do all the other benchmark numbers need to be sanity-checked as well? Are SOTA benchmarks really this difficult to get consistent, replicable results within a reasonable range of tolerance/variability? Can these benchmarks be compared from one paper to another, or are they only valid to compare intra-paper results?
by nerdsniper
Isn’t it just hilarious that a model that seemed so superior to Fable but didn't get doomsay marketing from Anthropic got released without any issues? In theory, this was supposed to be AGI level according to Anthropic, yet here we are, just a normal Friday.
by HyperL0gi
https://www.anthropic.com/news/claude-opus-5 - A blog post for those not wanting to go through a 190ish page pdf
by rb2e
Looking at all these releases it’s not a surprise that model routing is the fastest growing segment in AI right now.
There are 10+ LLM companies, each with dozens of models of different modalities, each model with multiple size variants, then different “thinking” levels, then agentic modes, “pro” modes, a “fast” option, standard vs flex vs batch execution. And of course each end combination has a different input/output/cache token price.
Companies that say “give me a prompt and I’ll route it to the most ideal and cost effective model and setting for you” are capturing a ton of value from a gap that model developers don’t seem to understand exists.
by paxys
Doing testing with it now, specifically for image->html conversion.
Previously Fable was the best at this, followed by Gemini 3.1 pro (a surprising #2, but Google has great vision models).
Opus' results seem to be more accurate than Fable, following the design source of truth better.
Example results:
Design source of truth: https://image.non.io/73e239a3-880f-4793-b65f-4810be2d9378.we...
Opus 5 build: https://html.non.io/solaraOpus/
Fable 5 build: https://html.non.io/solara/
Note the buttons - for fable they're pill buttons, opus got the rounded rectangle nature of them. Opus' images are closer to the source of truth as well (both LLMs were provided with image gen capabilities for the assets).
Running more tests now, but preliminary results are saying this is indeed better than Fable in some areas. Crazy.
by jjcm
I compared the writing style of Opus 5 vs Fable 5, and Opus 5 continues many of the "Claude-isms" of its 4.8 predecessor in a way that Fable broke away from.
Opus 5 still uses "carry the argument", "worth stating plainly", ", and the trap", "The X matters more", the use of "move"
We need an "annoying English" benchmark.
- Fable 5 Max: https://gist.github.com/deet/3d97f854b48eac6658d642fa18bb24d...
- Opus 5 Max: https://gist.github.com/deet/1a43693a732dfccb4d0d914bfc42692...
by deet
I think the most important thing here is not absolute performance. It's that organizations now have access to a Fable-ish model without Fable's 30-day data retention requirement[0].
> "Consistent with prior Opus models, Opus 5 does not have data retention requirements for general access."[1]
On the Opus model release page, the reason why Fable doesn't have an ARC-AGI score is because of that retention policy[2].
0: https://support.claude.com/en/articles/15425996-data-retenti...
by postalcoder
"Opus 5 was given a drawing of a machine part and asked to write code to rebuild it as a 3D FreeCAD model. However, in this task, the model was intentionally given no way to directly view the drawing. Opus 5 responded by writing its own computer vision pipeline to pull the geometry from the raw pixels, then reconstructed the full machine part."
How surreal is it that we are not absolutely jaw-dropped by these types of capability improvements? It's been less than 4 years since ChatGpt came out and now they are spontaneously building their own ML pipelines to do real-world 3D modeling tasks reliably.
Escaped its sandbox and hacked into Hugging Face's database? it's just another Monday...
That jump to 30% in ARC-AGI 3? Normal...
We should find a way to get "re-sensitized" to what we are witnessing and the pace of it.
by makaking
Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- Edit: It was pointed out to me that Opus 4.8 got "21%" for successfully fully completing ~1-in-5 tasks, but also got "55.7%" for obtaining significant partial credit on some of the ~4-in-5 tasks it could not fully complete.
---------------
Why does Anthropic say here that Opus 4.8 scored 55.7% on OSWorld 2.0 benchmark, but the paper published by the authors of OSWorld 2.0 say they achieved a benchmark of ~21% with Opus 4.8? [0]
That's a huge gap, considering that the paper was published just 2-4 weeks ago.
I understand that the benchmark authors have an incentive to publish lower numbers (to show that the benchmark has potential longevity) and that Anthropic has incentive to publish higher numbers, but the other models seem pretty inflated as well. The benchmark authors shows GPT-5.5 at 14%, and Anthropic shows GPT-5.6 Sol at 62.6%.
Is there any reasonable explanation for this? Do all the other benchmark numbers need to be sanity-checked as well? Are SOTA benchmarks really this difficult to get consistent, replicable results within a reasonable range of tolerance/variability? Can these benchmarks be compared from one paper to another, or are they only valid to compare intra-paper results?
by nerdsniper - Isn’t it just hilarious that a model that seemed so superior to Fable but didn't get doomsay marketing from Anthropic got released without any issues? In theory, this was supposed to be AGI level according to Anthropic, yet here we are, just a normal Friday.by HyperL0gi
- https://www.anthropic.com/news/claude-opus-5 - A blog post for those not wanting to go through a 190ish page pdfby rb2e
- Looking at all these releases it’s not a surprise that model routing is the fastest growing segment in AI right now.
There are 10+ LLM companies, each with dozens of models of different modalities, each model with multiple size variants, then different “thinking” levels, then agentic modes, “pro” modes, a “fast” option, standard vs flex vs batch execution. And of course each end combination has a different input/output/cache token price.
Companies that say “give me a prompt and I’ll route it to the most ideal and cost effective model and setting for you” are capturing a ton of value from a gap that model developers don’t seem to understand exists.
by paxys - Doing testing with it now, specifically for image->html conversion.
Previously Fable was the best at this, followed by Gemini 3.1 pro (a surprising #2, but Google has great vision models).
Opus' results seem to be more accurate than Fable, following the design source of truth better.
Example results:
Design source of truth: https://image.non.io/73e239a3-880f-4793-b65f-4810be2d9378.we...
Opus 5 build: https://html.non.io/solaraOpus/
Fable 5 build: https://html.non.io/solara/
Note the buttons - for fable they're pill buttons, opus got the rounded rectangle nature of them. Opus' images are closer to the source of truth as well (both LLMs were provided with image gen capabilities for the assets).
Running more tests now, but preliminary results are saying this is indeed better than Fable in some areas. Crazy.
by jjcm - I compared the writing style of Opus 5 vs Fable 5, and Opus 5 continues many of the "Claude-isms" of its 4.8 predecessor in a way that Fable broke away from.
Opus 5 still uses "carry the argument", "worth stating plainly", ", and the trap", "The X matters more", the use of "move"
We need an "annoying English" benchmark.
- Fable 5 Max: https://gist.github.com/deet/3d97f854b48eac6658d642fa18bb24d...
- Opus 5 Max: https://gist.github.com/deet/1a43693a732dfccb4d0d914bfc42692...
by deet - I think the most important thing here is not absolute performance. It's that organizations now have access to a Fable-ish model without Fable's 30-day data retention requirement[0].
> "Consistent with prior Opus models, Opus 5 does not have data retention requirements for general access."[1]
On the Opus model release page, the reason why Fable doesn't have an ARC-AGI score is because of that retention policy[2].
0: https://support.claude.com/en/articles/15425996-data-retenti...
by postalcoder - "Opus 5 was given a drawing of a machine part and asked to write code to rebuild it as a 3D FreeCAD model. However, in this task, the model was intentionally given no way to directly view the drawing. Opus 5 responded by writing its own computer vision pipeline to pull the geometry from the raw pixels, then reconstructed the full machine part."
How surreal is it that we are not absolutely jaw-dropped by these types of capability improvements? It's been less than 4 years since ChatGpt came out and now they are spontaneously building their own ML pipelines to do real-world 3D modeling tasks reliably.
Escaped its sandbox and hacked into Hugging Face's database? it's just another Monday...
That jump to 30% in ARC-AGI 3? Normal...
We should find a way to get "re-sensitized" to what we are witnessing and the pace of it.
by makaking