FrontierCode 1.1 shows Opus 5 can score lower under stricter reasoning settings
andrew_n_carr · x · 2026-07-25
- A repost says Opus 5 actually scores lower on FrontierCode 1.1 when using xhigh and max reasoning settings.
- The poster’s investigation claims the benchmark’s scope metric penalizes Opus 5 for making changes that are unrelated to the task.
- The attached chart compares models on FrontierCode 1.1 Main with score vs. cost, showing Opus 5 near the top but not clearly dominant across all settings.
- The takeaway is that the headline benchmark number may be sensitive to rubric details, especially how “scope” is judged.
Related event: Opus 5 Coding Paradox: Higher Reasoning Leads to Lower Scores(13 posts)→
More from Models
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11
- awesome-llm-leaderboards: an open-source directory of LLM leaderboards, pricing tables, comparison tools — Last_Establishment_1 · 2026-09-11
- Anthropic claims it works to keep eval environments unidentifiable to models — MaxKannen · 2026-09-11
- Nex N2.5 Pro released on Hugging Face with 407GB of weights — jinnyjuice · 2026-09-11
- RoMa v2 image matching model unveiled in the usual black poster — ducha_aiki · 2026-09-11
- OpenAI rated Astra 'Critical' for cyber capabilities — and admits it's harder to monitor — theguywhobuilds · 2026-09-11