Grok 4.5 Tops Real-World Task Benchmark
XFreeze · x · 2026-07-11
Grok 4.5 secured #1 on AutomationBench-AA, which measures real-world AI automation capabilities.
- Scored 51%, beating Claude Fable 5 (49%) and Claude Opus 4.8 (48%)
- Claims to cost roughly 1/4 of competitors per task
- Uses only about 8K output tokens per task, which the author notes is highly token-efficient for a frontier model
The post emphasizes that Grok 4.5 isn't just leading in scores, but also stands out in cost and token efficiency for real-world tasks.
More from coding & agent
- charlie Marsh: rewrites beat external deps in the AI era — mohamedmansour · 2026-10-26
- OpenAI and Twitch launch Codex hackathon with $25,000 in prizes — OpenAIDevs · 2026-10-26
- Filtering secrets on the write path: why agent memory deserves more suspicion at ingest than retrieval — Classic-Being-7960 · 2026-10-26
- INT21's AI agent swarm rewrote Drama 3's inference runtime in Rust within one hour, beating SGLang-Omni — bingxu_ · 2026-10-26
- After OpenCode key leak: 5 practical rules for keeping keys away from agents — jacobholm_dev · 2026-10-26
- wandb 0.31.0 ships with 2x faster startup, adds JSON output for coding agents — wandb · 2026-10-26