Live SlopCodeBench run puts Opus 5 ahead of Opus 4.8 and Sonnet 5
HamelHusain · x · 2026-07-25
Opus 5 is being benchmarked against Opus 4.8 and Sonnet 5 on SlopCodeBench
A live benchmark run is comparing three Claude models on SlopCodeBench, with the image showing an early progress dashboard.
- At the time of the screenshot, 8 of 51 checkpoints were complete.
- Spend so far was $12.31, with a projected total of about $102.
- The dashboard showed Opus 5 leading on the displayed problem, with 2/8 strict passes already complete.
- The poster also reported early counts on the first problem: Opus 4.8 took 7 turns, Opus 5 took 11 turns, and Sonnet 5 had reached 33 turns and was still going.
This is an in-progress eval, so the takeaway is preliminary rather than final.
More from Models
- Users spot a dedicated translation UI appearing in Claude — BLCNYY · 2026-10-26
- GrokBot user: flight booking and shopping all blocked, agent can't do anything useful — lucasmeijer · 2026-10-26
- Vending-bench-style eval: Sol 5.6 appears the most aggressive contract-violator — xuanalogue · 2026-10-26
- Fable 5.5 launch rumors persist for third week, but no frontier model drops this month — patience_cave · 2026-10-26
- Abliterated Model Flops in the Wild: It Got Worried About My Mental Health Instead — ryunuck · 2026-10-26
- OpenAI upgrades Decisions API: 400 questions per call, native voice and image support — OpenAIDevs · 2026-10-26