Claude Opus 5.5 vs GPT-6.1 Sol
The two side by side on the four things we rate, using public benchmark data. Every score links to its source on each model's page.
| What we rate | Claude Opus 5.5 | GPT-6.1 Sol |
|---|---|---|
| Writing writing votes | Top tier 1st of 77 listed | Middle 54th of 77 listed |
| Coding coding votes | Top tier 1st of 77 listed | Strong 37th of 77 listed |
| Maths hard maths problems | Top tier 3rd of 43 listed | Top tier 1st of 43 listed |
| Knowledge short factual questions | Top tier 4th of 43 listed | Top tier 3rd of 43 listed |
Claude Opus 5.5 ranks higher on writing and coding. GPT-6.1 Sol ranks higher on maths and knowledge. A few places apart can sit inside the margin of error, so open the full comparison to see the ranges. We do not pick an overall winner: the better choice depends on the job.
Open the full interactive comparison Find my AI
Claude Opus 5.5
By Anthropic. Full profile and sources
Good at
- Coding: Top tier (1st of 77 listed models)
- Knowledge: Top tier (4th of 43 listed models)
- Maths: Top tier (3rd of 43 listed models)
Not so good at
None of the four main ratings puts it behind the others. That is not evidence it has no weak spots.
- Closed weights: only its maker and chosen partners can offer it
Can't tell yet
- Fixing real software bugs: Not enough data
- Price not independently verified
Where it is one of our picks
- Writing and creating content: best-supported choice.
- Coding and building things: best-supported choice.
- Homework and maths: good-enough alternative.
- Business emails and everyday work: good-enough alternative.
- Research and checking facts: good-enough alternative.
Price: Price not independently verified
GPT-6.1 Sol
By OpenAI. Full profile and sources
Good at
- Coding: Strong (37th of 77 listed models)
- Knowledge: Top tier (3rd of 43 listed models)
- Maths: Top tier (1st of 43 listed models)
- Relatively stronger on Expert-level prompts: 26th of 77, against 53rd overall
Not so good at
- Writing: Middle (54th of 77 listed models)
- Closed weights: only its maker and chosen partners can offer it
Can't tell yet
- Fixing real software bugs: Not enough data
Where it is one of our picks
- Homework and maths: best-supported choice.
- Research and checking facts: good-enough alternative.
Price: Verified: ChatGPT Plus GBP 20.00 a month (checked 29 Oct 2026); ChatGPT Pro (from) GBP 89.00 a month (checked 29 Oct 2026)
Ratings compare only the 77 models listed here, in quarters, best first. Not enough data means no result yet, never a low score. How we test.