DeepSeek V4.1 Flash (Max)
- Cost
- $1.03
- Time Spent
- 2h 22m
- Harness
- OpenCode · v2.0.32
- Model version
- 1017
- Tokens in / out
- 4.2M / 90.7K
- Date
Accuracy
12.7%
How closely this build matches the reference model.
3D view
Loading 3D model…
Drag the divider to reveal the build · drag the model to orbit · scroll to zoom
Model views
front
Loading front comparison images
back
Loading back comparison images
left
Loading left comparison images
right
Loading right comparison images
Details
- Parts placed
- 106
- Reference parts
- 314
- Parts matched
- 28
- Positions matched
- 0
- Orientations matched
- 0
- Surplus parts
- 0
- Match
- 0.030
- Bad parts
- 0
- Structural
- 1
- Car shape
- 0.500
Other builds of this benchmarkOther AI models, coding harnesses or reasoning effort levels on this same benchmark. Each row represents one setup and shows its build with the highest reference-accuracy score. Rows run from the highest score to the lowest. This build's setup is excluded.
| Harness · model | Accuracy | Cost | Time Spent |
|---|---|---|---|
| Codex · GPT 6 Astra (Xhigh) | 85.4% | $11.54 | 29m 52s |
| Codex · GPT 6 Astra (Ultra) | 84.9% | $22.19 | 1h 33m |
| Claude Code · Claude Sonnet 5.5 (Xhigh) | 70.2% | $135.43 | 3h 39m |
| Codex · GPT 6.1 Sol (Ultra) | 65.1% | $6.96 | 3h 47m |
| Codex · GPT 6.1 Sol (Xhigh) | 45.6% | $9.85 | 3h 59m |
| Claude Code · Claude Opus 5.5 (Xhigh) | 27.9% | $60.49 | 3h 10m |
| Claude Code · Claude Fable 5.1 (Max) | 19.0% | $89.40 | 2h 48m |
| Claude Code · Claude Haiku 5.5 (Xhigh) | 18.9% | $6.33 | 1h 53m |
| Claude Code · Claude Haiku 5.5 (Max) | 16.4% | $1.71 | 1h 9m |
| Grok Build · Grok 4.6 (Xhigh) | 12.4% | $10.77 | 58m 23s |
| Codex · GPT 6 Luna (Max) | 10.0% | $1.76 | 3h 49m |
