FrontierCode charts show Claude Opus 5 peaking at medium reasoning effort
zainhas · x · 2026-07-25
A FrontierCode benchmark chart suggests Claude Opus 5 may be sensitive to test-time compute settings.
On the main set, the model scores best around medium reasoning effort at 53.4%, then falls at higher settings before recovering somewhat at max. On the extended set, it peaks around medium as well, reaching 63.6% and then dropping at higher effort levels. The post frames this as a possible overthinking problem: more reasoning compute does not always improve results.
Related event: Opus 5 Coding Paradox: Higher Reasoning Leads to Lower Scores(13 posts)→
More from Models
- Astra Scores 83% on GauntletBench, First Computer-Use Agent to Beat Human Baseline — ducha_aiki · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11
- TheZvi Polls: Has Your Coding Model Choice Changed Since Fable 5.1 and Astra? — TheZvi · 2026-09-11