Subway Scheduling on NYC Queens (out-of-domain)
155.75Electricity ConsumptionMiniMax-M2.5
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MiniMax-M2.5Framework=TrafficClaw2026.04 | 155.75 | 722.67 | |
| Qwen3-235BFramework=TrafficClaw2026.04 | 163.48 | 249.9 | |
| AIDE2026.04 | 174.99 | 195.32 | |
| Classic Method2026.04 | 185.11 | 761.33 | |
| TrafficClaw (8B)Model size=8B2026.04 | 194.23 | 177.03 | |
| Qwen3-32BFramework=TrafficClaw2026.04 | 194.89 | 313.98 | |
| o4-miniFramework=TrafficClaw2026.04 | 208.9 | 392.94 | |
| Qwen3-8BFramework=TrafficClaw2026.04 | 209.41 | 286.84 | |
| Gemini-3.1-ProFramework=TrafficClaw2026.04 | 215.54 | 213.34 | |
| TrafficGPT2026.04 | 218.45 | 391.12 | |
| SUMO-MCP2026.04 | 232.37 | 216.26 | |
| Kimi-K2.5Framework=TrafficClaw2026.04 | 249.85 | 312.08 | |
| DeepSeek-V3.2Framework=TrafficClaw2026.04 | 292.05 | 367.36 |