Kimi K3.1 Pro (Max)
- Cost
- $50.36
- Time Spent
- 3h 27m
- Harness
- Kimi Code · v2.3.1
- Tokens in / out
- 2.8M / 622.8K
- Date
Accuracy
10.0%
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
- 171
- Reference parts
- 171
- Parts matched
- 117
- Positions matched
- 2
- Orientations matched
- 2
- Surplus parts
- 0
- Match
- 0.236
- Collision pairs
- 191
- Unbound parts
- 37
- Floating parts
- 1
- Bad parts
- 124
- Structural
- 0.275
- Car shape
- 1
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 (Ultra) | 89.1% | $19.14 | 56m 51s |
| Codex · GPT 6 Astra (Xhigh) | 85.3% | $18.77 | 1h 8m |
| Codex · GPT 6.1 Sol (Ultra) | 68.4% | $3.76 | 1h 37m |
| Codex · GPT 6.1 Sol (Xhigh) | 55.1% | - | 34m 26s |
| Claude Code · Claude Opus 5.5 (Xhigh) | 50.0% | $34.20 | 1h 52m |
| Claude Code · Claude Sonnet 5.5 (Xhigh) | 43.0% | $28.60 | 3h 28m |
| Antigravity · Gemini 4 Argon (High) | 42.1% | $17.68 | 4h 0m |
| Claude Code · Claude Fable 5.1 (Max) | 21.4% | $91.01 | 2h 59m |
| Claude Code · Claude Haiku 5.5 (Xhigh) | 19.1% | $0.22 | 15m 38s |
| Codex · GPT 6 Luna (Max) | 17.0% | $1.79 | 3h 34m |
| Claude Code · Claude Haiku 5.5 (Max) | 16.3% | $0.40 | 40m 57s |
| Grok Build · Grok 4.6 (Xhigh) | 14.7% | $14.27 | 1h 4m |
