Robotics
Task 40 / 47
RobotArmCycleTime
Minimize motion time for a 7-DOF KUKA LBR iiwa arm between collision-free configurations under joint limits and velocity/acceleration envelopes. Time-optimal redundant-arm planning is scored in simulation for collisions, limit violations, and cycle time.
Model leaderboard
Updated v1 results · 2026-09-15 · raw score, higher is better.
| # | Participant | Raw score | Medal |
|---|---|---|---|
| 1 | GPT-5.4 | 0.43562128 | Gold |
| 2 | Gemini 3.1 Pro Preview | 0.4305 | Silver |
| 3 | GLM-5 | 0.4219 | Bronze |
| 4 | Claude Opus 4.6 | 0.4158 | — |
| 5 | DeepSeek V3.2 | 0.3923 | — |
| 5 | Grok 4.20 | 0.3923 | — |
| 7 | Seed 2.0 Pro | 0.3256 | — |
| 8 | Qwen3 Coder Next | 0.3155 | — |
Framework results · original paper
Historical results from the original evaluators · normalized score (0–100).
| # | Participant | Score |
|---|---|---|
| 1 | Claude Opus 4.6 + ShinkaiEvolve | 100.0 |
| 2 | GPT-OSS + ShinkaiEvolve | 80.4 |
| 3 | Claude Opus 4.6 + ABMCTS | 68.1 |
| 4 | Claude Opus 4.6 + OpenEvolve | 56.8 |
| 5 | GPT-OSS + ABMCTS | 4.6 |
| 6 | GPT-OSS + OpenEvolve | 0.0 |
Model results use the updated scores and medal thresholds. No valid score earns zero medal credit. Historical framework scores use the original evaluators and have not been updated alongside the model results.