← comparisons · head to head
Grok 4.7 vs Grok 4.6
Of the 4 public leaderboards that rate both, Grok 4.7 scores higher on 3 and Grok 4.6 on 1. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Grok 4.7 is at 69.4 and Grok 4.6 at 60 (out of 100).
Scores as published by each board; table composed September 28, 2026.
Get the next launch alert, free →
Leaderboard by leaderboard
| Board | Grok 4.7 | Grok 4.6 | Higher |
|---|---|---|---|
| LMArena Elo (community votes) | 1,629.3 | 1,620.6 | Grok 4.7 |
| LiveBench global average (0-100) | 77.4 | 78 | Grok 4.6 |
| Vals AI Vals Index accuracy % · weighted finance + coding tasks | 60.2 | 59.2 | Grok 4.7 |
| Artificial Analysis intelligence index · measured runs only | 46.4 | 44.3 | Grok 4.7 |
Raw scores are each board's own scale, so compare within a row, not across rows. Full table: the bench index.
For coding
On the ArtificialWatch coding index, Grok 4.7 is at 33.3 (#21 of 31) and Grok 4.6 at 43.3 (#17). Grok 4.7 scores higher on 1 of the 3 coding boards that rate both and Grok 4.6 on 2.
| Coding board | Grok 4.7 | Grok 4.6 |
|---|---|---|
| LMArena · Coding | 1,488.3 | 1,507.4 |
| LiveBench · Coding | 65.6 | 66.9 |
| Vals Vibe Code Bench | 86.2 | 76.2 |
Grok 4.7 at a glance
- Developer
- xAI
- Status
- Live since September 21, 2026
- API price
- $2 input / $6 output per 1M tokens · xAI, grok-4.7
- Context window
- 500K tokens
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.
Grok 4.6 at a glance
- Developer
- xAI
- Status
- Live since August 12, 2026
- API price
- $2 input / $6 output per 1M tokens · xAI, grok-4.6
- Context window
- 500K tokens
Live — Aug 12 at $2/$6 per 1M, unchanged from Grok 4.5.
Grok 4.7 vs Grok 4.6: quick answers
Which is better, Grok 4.7 or Grok 4.6?
It depends on what you measure. Of the 4 public leaderboards that rate both, Grok 4.7 scores higher on 3 and Grok 4.6 on 1. Grok 4.7's widest lead is on Artificial Analysis; Grok 4.6'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 69.4 and Grok 4.6 at 60 (out of 100).
Which is newer, Grok 4.7 or Grok 4.6?
Grok 4.7. It went live on September 21, 2026, 40 days after Grok 4.6 (August 12, 2026).
Which is cheaper, Grok 4.7 or Grok 4.6?
They cost the same per token. On each vendor's own API, Grok 4.7 is $2 input / $6 output per million tokens and Grok 4.6 is $2 input / $6 output per million tokens. Grok 4.7's rate rises for prompts over 200K tokens; Grok 4.6's rate rises for prompts over 200K tokens. Prices as published in the models.dev catalog, as of 2026-09-27.
Which has the bigger context window, Grok 4.7 or Grok 4.6?
Neither. Both take 500K tokens.
How do Grok 4.7 and Grok 4.6 compare for coding?
On the ArtificialWatch coding index, Grok 4.7 is at 33.3 (#21 of 31) and Grok 4.6 at 43.3 (#17). Grok 4.7 scores higher on 1 of the 3 coding boards that rate both and Grok 4.6 on 2.
Who makes Grok 4.7 and Grok 4.6?
Both are from xAI.
Where do these numbers come from?
Each score is the leaderboard's own published figure, read by ArtificialWatch (table composed September 28, 2026). Boards measure different things, so raw scores are only comparable within a row.
More comparisons
Hear the minute the next one drops. Free.
A free Chrome push the moment a new model answers on a public API, an email about 15 minutes later. Texts or a phone call on paid plans.
- Free forever
- No card
- Unsubscribe in one click
Also: the bench index · API pricing · the wire