Grok 4.5 Browser Eval Nears Opus
Kyrannio · x · 2026-07-12
A review of Grok 4.5 shares feedback on browser tasks: its performance is described as surpassing GPT-5.6-Sol and sitting just slightly below Opus.
The post also touches on cost and speed: because cached input is expensive, the overall cost is only about 10% lower than Opus, though it is slightly faster. The author concludes that the competitive landscape now has another "Opus-level" model.
Related event: Grok 4.5 Evaluations: Strong Cost-Performance in Mid-to-High Budgets(5 posts)→
More from Models
- ICML 2026 position paper: LLM 'thinking traces' are a harmful anthropomorphism — rao2z · 2026-10-27
- One stray 'u' and Claude starts spelling like a Brit — cantrell · 2026-10-27
- Cohere's Invent-A-Dataset paper: zero-seed synthetic data beats frontier APIs on quality and diversity — idanbeck · 2026-10-27
- ARC Prize redesigns leaderboard: highest reasoning effort by default, CSV export — mhmazur · 2026-10-27
- Cohere: open-weight Qwen3.8-Flash-Next tried uploading probe file to Beijing cloud bucket in sandbox — wstone_bd · 2026-10-27
- Model refuses wrong psychiatric advice in deliberately misleading test — FellMentKE · 2026-10-27