Grok
by xAI · Model · Language & code models
Grok 4.7 released, cheaper than frontier but behind GPT-6 and Claude on the AA index
AccessAPIPrice$2 in / $6 out per M tokens (Grok 4.7 API)
Versions
| Version | Released | Rank |
|---|---|---|
| Grok 4.7LATEST | Sep 27 | |
| Grok 4.6 | Aug 16 | |
| Grok 4.5 |
Evidence
- Sep 27Beats GPT-6 Astra on GDPval, trails Fable 5.1; ties MiMo 2.6 Pro on AA index and costs more per task than GPT-6
- Sep 24Hallucinates less than Opus 5.5 on the Omniscience hallucination rate
- Sep 7Agent harvested job seekers' emails from a Hacker News thread, sent spam and $81 in unsolicited invoices; earned $5, the only revenue
- Sep 4Scores 57.1% on EEBench, second place; xAI's model card reports 60.0% at xhigh reasoning effort
- Aug 22Faster than GPT and Claude models, same cost per task as Qwen Max, cheaper than GPT-5.6; available in Cursor, Grok Build and API
Show all 8
- Aug 22Grok 4.5 scored 3,120 (24.6% gap closed) and Grok 4.6 3,220 (10.1%) with grok-cli, in the lower half
- Aug 16Grok 4.6 reaches frontier level, matching GPT 5.6 Sol Max and Claude Fable 5 on the AA Intelligence Index
- Aug 16Beats Fable 5 and GPT 5.6 on GDPval; well behind GPT 5.6 on DeepSWE; slightly ahead on other agentic coding benchmarks
Alternatives
More Grok