List your company

Holistic Evaluation on CodaSet ID Average (test)

90.6AccuracyQwen3-235B-A22B
71.661676.578381.49586.4117May 25, 2026

Evaluation results

MethodLinks
Qwen3-235B-A22B2026.0590.65
DeepSeek-V3.12026.0589.745.2
DecoRfallback_model=DeepSeek-V3.12026.0589.352.1
DecoRfallback_model=gpt-oss-120b2026.0589.131.9
gpt-oss-120b2026.0588.712.7
DeepSeek-V3.2-Exp2026.0588.513.9
Kimi-K2-Instruct2026.0587.9411.9
MODEL-SAT2026.0587.57.8
EmbedLLM2026.0586.84.2
RouterDC2026.0586.774.2
KNN Router2026.0586.62
Random Router2026.0584.184.4
gemma-3-27b-it2026.0583.792.4
gemma-3-12b-it2026.0582.831
LLM Router2026.0582.232.3
Mistral-Small-3.2-24B2026.0572.391.8