List your company

Question Answering on GPQA & MMLU-Pro (OOD Average)

83.3AccuracyQwen3-235B
48.25257.35166.4575.549Jun 28, 2026

Evaluation results

MethodLinks
Qwen3-235BCategory=Heuristic2026.0683.30.004
ENTROROUTER2026.0679.50.002
Qwen3-30BCategory=Heuristic2026.0678.80
RandomCategory=Heuristic2026.0678.40.002
FORCCategory=Existing Routing Architectures2026.0677.50.002
RouteLLMCategory=Existing Routing Architectures2026.0675.80.001
Qwen3-4BCategory=Heuristic2026.0673.30
xRouterCategory=Existing Routing Architectures2026.0650.70
Router-R1Category=Existing Routing Architectures2026.0649.60