Muse Spark 1.3
Meta. Run in Cline CLI, OpenCode. Cline free tier.
24 runs on 12 prompts · 96% finished
Results
The best run of each of its 12 tests first, then every other run. Filter them in the explorer
23 finished runs
Numbers: finish rate, cost, wall time, draft scores
- Runs
- 24
- on 12 prompts
- Finished
- 96%
- 23 of 24
- Median cost, finished run
- $0
- n=18
- Median wall time, finished run
- 5m 20s
- n=23
- Recorded spend
- $0
- $0 on unfinished runs; 6 without a recorded cost
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
- 23 of 24 runs finished: 8th of 24 models with at least 3 (finish rate)
- $0 (n=18): 1st of 14 models with at least 3 (median cost of a finished run)
Weaknesses
- Other unfinished runs, not counted against the model: 1 INFRA
Best and hardest run
Best run
Picked as its fastest finished run (no scored result yet).
-
Muse Spark 1.3, Cline CLI, whale_clouds
Cline CLI 3.0.65, high effort
skills off
1m 53s
not recorded: the run's token counts were never reported, so there is no estimate
OK
Unscored: no rubric for this prompt
Hardest run
Picked as its slowest finished run.
-
Muse Spark 1.3, Cline CLI, DualSense controller, max fidelity
Cline CLI 3.0.65, high effort
skills off
56m 12s
not recorded: the run's usage was never recorded
OK
Unscored: no rubric for this prompt
Draft scores by prompt
No scored result yet (only prompts with a published rubric are scored).
By harness
| Cline CLI | 12 | 12 | 100% | $0 n=7 | 4m 35s n=12 |
|---|---|---|---|---|---|
| OpenCode | 12 | 11 | 92% | $0 n=11 | 5m 38s n=11 |
All 12 tests and experiment collections
- Pelican car france (2 runs)
- Dolphin vlog bicycle (2 runs)
- Whale clouds (2 runs)
- BMW M4 Competition, side view (flat vector) (2 runs)
- Xbox 360 controller (2 runs)
- California brown pelican riding a bicycle (detailed spec) (2 runs)
- DualSense controller, max fidelity (2 runs)
- Animated pelican riding a bicycle (SMIL/CSS) (2 runs)
- Isometric SVG town with sprite sheet (2 runs)
- Lighthouse on a headland at night (2 runs)
- MacBook Pro 16" realistic 3D render (Playcode benchmark) (2 runs)
- Pelican riding a bicycle (control) (2 runs)
Experiment collections: SVG (24) · Harness lane (24) · Free lane (18)