Grok 4.7
xAI. Run in Grok Build, OpenCode.
10 runs on 6 prompts · 100% finished
Results
The best run of each of its 6 tests first, then every other run. Filter them in the explorer
10 finished runs
Numbers: finish rate, cost, wall time, draft scores
- Runs
- 10
- on 6 prompts
- Finished
- 100%
- 10 of 10
- Median cost, finished run
- $6.29
- n=10
- Median wall time, finished run
- 36m 49s
- n=10
- Recorded spend
- $65.07
- $0 on unfinished runs
From the numbers
Set against the other models with at least 3 runs (top or bottom third), and its draft-score ranks within single prompts. Nothing here is averaged across prompts.
Strengths
- 10 of 10 runs finished: 1st of 24 models with at least 3 (finish rate)
- Draft score 9.5/10 on Pelican riding a bicycle (control) (in Grok Build): ranked 1st of 13
- Draft score 8.5/10 on Lighthouse on a headland at night (in Grok Build): ranked 2nd of 12
- Draft score 9.5/10 on Isometric SVG town with sprite sheet (in Grok Build): ranked 2nd of 11
Weaknesses
- 36m 49s (n=10): 23rd of 23 models with at least 3 (median wall time of a finished run)
- $6.29 (n=10): 13th of 14 models with at least 3 (median cost of a finished run)
- Draft score 7.5/10 on Lighthouse on a headland at night (in OpenCode): ranked 9th of 12
- Draft score 7.5/10 on Pelican riding a bicycle (control) (in OpenCode): ranked 11th of 13
- Draft score 8.5/10 on Animated pelican riding a bicycle (SMIL/CSS) (in OpenCode): ranked 11th of 12
- Draft score 4.5/10 on MacBook Pro 16" realistic 3D render (Playcode benchmark) (in OpenCode): ranked 12th of 12
Best and hardest run
Best run
Picked as its best draft-score rank on a prompt.
-
Grok 4.7, Grok Build, Pelican riding a bicycle (control)
Grok Build 1.0.41, xhigh effort, via xAI
skills off
30m 14s
$2.98 reported by Grok Build est. $2.98
OK
AI judge 9.5/10 Draft scorerubric
Hardest run
Picked as its lowest draft-score rank on a prompt.
-
Grok 4.7, OpenCode, MacBook Pro 16" realistic 3D render (Playcode benchmark)
OpenCode 1.18.32, xhigh effort, via xAI
skills off
40m 31s
$15.78 reported by OpenCode est. $15.78
OK
AI judge 4.5/10 Draft score Criterion breakdown unavailablerubric
Draft scores by prompt
| Isometric SVG town with sprite sheet | Grok Build | 9.5/10 draft | 2nd of 11 |
|---|---|---|---|
| Isometric SVG town with sprite sheet | OpenCode | 9/10 draft | 8th of 11 |
| Lighthouse on a headland at night | Grok Build | 8.5/10 draft | 2nd of 12 |
| Lighthouse on a headland at night | OpenCode | 7.5/10 draft | 9th of 12 |
| MacBook Pro 16" realistic 3D render (Playcode benchmark) | Grok Build | 8.5/10 draft | 6th of 12 |
| MacBook Pro 16" realistic 3D render (Playcode benchmark) | OpenCode | 4.5/10 draft | 12th of 12 |
| Pelican riding a bicycle (control) | Grok Build | 9.5/10 draft | 1st of 13 |
| Pelican riding a bicycle (control) | OpenCode | 7.5/10 draft | 11th of 13 |
| Animated pelican riding a bicycle (SMIL/CSS) | OpenCode | 8.5/10 draft | 11th of 12 |
By harness
| OpenCode | 6 | 6 | 100% | $7.65 n=6 | 31m 01s n=6 |
|---|---|---|---|---|---|
| Grok Build | 4 | 4 | 100% | $4.50 n=4 | 38m 25s n=4 |
All 6 tests and experiment collections
- Isometric SVG town with sprite sheet (2 runs)
- Pelican riding a bicycle (control) (2 runs)
- Animated pelican riding a bicycle (SMIL/CSS) (1 run)
- Lighthouse on a headland at night (2 runs)
- MacBook Pro 16" realistic 3D render (Playcode benchmark) (2 runs)
- DualSense controller, max fidelity (1 run)
Experiment collections: SVG (10) · Harness lane (10)