Will GPT-5.2 exceed Claude Opus 4.5 on SWE-bench?
5
Ṁ100Ṁ260resolved Dec 14
Resolved
NO1H
6H
1D
1W
1M
ALL
Resolves yes if GPT-5.2 exceeds Claude Opus 4.5 on SWE-bench. For this market a model counts as “GPT-5.2” if it appears to be a successor to GPT-5.1 regardless of its actual name
This question is managed and resolved by Manifold.
Market context
Get 
1,000 to start trading!
1,000🏅 Top traders
| # | Trader | Total profit |
|---|---|---|
| 1 | Ṁ33 | |
| 2 | Ṁ19 | |
| 3 | Ṁ14 | |
| 4 | Ṁ4 | |
| 5 | Ṁ0 |
People are also trading
Related questions
Will GPT-5.3-Codex have a longer time-horizon than Claude Opus 4.6?
81% chance
Does GPT-5.5 exist?
67% chance
Will Claude Sonnet 5 exceed 85% on SWE-bench verified?
16% chance
Will GPT-5 be capable of achieving superhuman performance in at least one exam that is typically taken by humans?
91% chance
What will the aggregate improvement of GPT5 be over GPT4 in terms of metrics?
200
Will the performance jump from GPT4->GPT5 be less than the one from GPT3->GPT4?
79% chance