Mathematical Reasoning on SMT 2025
84.2AccuracyQwen3-235B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen3-235BMethod Category=Heuristic, Parameters=235B2026.06 | 84.2 | 0.9183 | |
| ENTROROUTERMethod Category=Routing Architecture2026.06 | 80.4 | 0.5155 | |
| FORCMethod Category=Existing Routing Architecture2026.06 | 77.6 | 0.5381 | |
| RandomMethod Category=Heuristic2026.06 | 76.4 | 0.4956 | |
| Qwen3-30BMethod Category=Heuristic, Parameters=30B2026.06 | 76.2 | 0.4983 | |
| RouteLLMMethod Category=Existing Routing Architecture2026.06 | 69.8 | 0.0712 | |
| Qwen3-4BMethod Category=Heuristic, Parameters=4B2026.06 | 65.3 | 0.0322 | |
| Router-R1Method Category=Existing Routing Architecture2026.06 | 35.4 | 0.0359 | |
| xRouterMethod Category=Existing Routing Architecture2026.06 | 34.4 | 0.0069 |