← comparisons · head to head
Grok 4.7 vs GPT-6 Astra
GPT-6 Astra scores higher than Grok 4.7 on all 4 public leaderboards that rate both. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Grok 4.7 is at 69.7 and GPT-6 Astra at 88.5 (out of 100).
Scores as published by each board; table composed September 24, 2026.
Get the next launch alert, free →
Leaderboard by leaderboard
| Board | Grok 4.7 | GPT-6 Astra | Higher |
|---|---|---|---|
| LMArena Elo (community votes) | 1,632.3 | 1,792.2 | GPT-6 Astra |
| LiveBench global average (0-100) | 77.4 | 82.2 | GPT-6 Astra |
| Vals AI Vals Index accuracy % · weighted finance + coding tasks | 60.2 | 66.6 | GPT-6 Astra |
| Artificial Analysis intelligence index · measured runs only | 46.4 | 52.7 | GPT-6 Astra |
Raw scores are each board's own scale, so compare within a row, not across rows. Full table: the bench index.
Grok 4.7 at a glance
- Developer
- xAI
- Status
- Live since September 21, 2026
Live — Sep 21 · 500k ctx · $2/$6 per 1M under a 200k prompt, $4/$12 over it, $0.50 cached — unchanged from 4.6 · Artificial Analysis: Intelligence Index 46 (+2), 4th on the Coding Agent Index at 56 with Grok Build, AA-Briefcase 1657 Elo (+111) alongside Opus 5 and Fable 5.1 · burns ~81k output tokens per index task at xhigh, 2.25x Grok 4.6.
Grok 4.7 puts xAI in the top four - and it buys that with three times the tokens
2026-09-21 · xAI shipped Grok 4.7 today. Our radar read the id at 15:49:44 UTC, confirmed it on the next sweep and sent 307 alerts 61 seconds after first sight.
Musk says Grok 4.6 ships next week — on the earnings call where SpaceX stock fell 8%
2026-08-05 · SpaceX held its first public earnings call yesterday. Grok was on the agenda, and the version of it circulating as a bullet list flattens three very different levels of certainty into one. Here they are separated.
GPT-6 Astra at a glance
- Developer
- OpenAI
- Status
- Live since September 3, 2026
Live — Sep 3, Trusted Access enterprises first; our own sweep read the plain id on OpenRouter at the base sticker Sep 4 21:16 UTC (openai/gpt-6-astra, $10/$50), and the Fast tier the same night (vercel/openai/gpt-6-astra-fast, $20/$100) · $10/$50 per 1M, $1 cached, 1.05M ctx / 128K out · AA Coding Agent Index 67 (≈ Opus 5, Fable 5), Intelligence Index 61 (= GPT-5.6 Sol, 5 below Fable 5.1).
GPT-6 Astra is out — Fable 5.1's sticker, trusted access first, public API within days
2026-09-03 · OpenAI shipped GPT-6 Astra today. Its own words, from the model documentation: "Our most capable model, built for the hardest end-to-end work" — complex reasoning, coding, computer use, research and document creation.
OpenAI is treating Astra as its first Critical cyber model — and slowing it down, 24 hours after the leaks said next week
2026-08-07 · Twenty-four hours ago both accounts we track said Astra was launching next week. Today OpenAI published that it is slowing the model down, and the reason outranks any launch calendar.
Grok 4.7 vs GPT-6 Astra: quick answers
Which is better, Grok 4.7 or GPT-6 Astra?
It depends on what you measure. GPT-6 Astra scores higher than Grok 4.7 on all 4 public leaderboards that rate both. GPT-6 Astra's widest lead is on LiveBench. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Grok 4.7 is at 69.7 and GPT-6 Astra at 88.5 (out of 100).
Which is newer, Grok 4.7 or GPT-6 Astra?
Grok 4.7. It went live on September 21, 2026, 18 days after GPT-6 Astra (September 3, 2026).
Who makes Grok 4.7 and GPT-6 Astra?
Grok 4.7 is from xAI; GPT-6 Astra is from OpenAI.
Where do these numbers come from?
Each score is the leaderboard's own published figure, read by ArtificialWatch (table composed September 24, 2026). Boards measure different things, so raw scores are only comparable within a row.
More comparisons
Watch free: Chrome push the moment a new model answers on a public API, an email about 15 minutes later. Also: the bench index · the wire