Grok 4.5 looks strong on ReactBench
aidenybai · x · 2026-07-21
ReactBench v1 is a benchmark for coding agents on realistic React work, aimed at catching issues that normal tests miss: performance, accessibility, and other production-quality problems.
The screenshot highlights results on the benchmark: GPT 5.6 Terra and Sol lead at 53% pass@1, followed by Fable 5 at 47%, GPT 5.6 Luna at 44%, and Cursor Grok 4.5 High at 40%. A second chart compares score vs. rollout cost, showing Grok 4.5 as relatively efficient at around $0.62 per rollout.
More from coding & agent
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Data engineering, not agent frameworks, is the real bottleneck for enterprise AI agents — dhruv2038 · 2026-09-11
- RTK Terminal Compression Cuts Tokens but Leaves Your AI Coding Bill Unchanged — Bartaseth · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11