List your company

Question Answering on Science Q&A Chemistry

83.8AccuracyClaude-Opus-4.6
46.15255.92665.775.474Apr 18, 2026

Evaluation results

MethodLinks
Claude-Opus-4.6Type=Proprietary, Evaluation Protocol=zero-shot2026.0483.80.0270.090.838
Qwen3-8B (CaOPD)Type=Ours, Evaluation Protocol=fine-tuned2026.0480.60.1410.1340.77
GPT-5.4Type=Proprietary, Evaluation Protocol=zero-shot2026.0472.90.080.1540.802
Claude-Sonnet-4.5Type=Proprietary, Evaluation Protocol=zero-shot2026.0472.40.1550.2010.874
Gemini-3.1-ProType=Proprietary, Evaluation Protocol=zero-shot2026.0471.90.2780.2760.997
Qwen3.5-397BType=Open-weight, Evaluation Protocol=zero-shot2026.0471.40.2140.2370.929
GPT-5.2Type=Proprietary, Evaluation Protocol=zero-shot2026.0463.30.1060.1730.608
Gemini-3.1-Flash-LiteType=Proprietary, Evaluation Protocol=zero-shot2026.0462.90.360.360.989
Gemini-2.5-ProType=Proprietary, Evaluation Protocol=zero-shot2026.0461.90.3650.3640.984
Kimi-K2.5Type=Open-weight, Evaluation Protocol=zero-shot2026.04600.3790.380.979
Gemini-2.5-FlashType=Proprietary, Evaluation Protocol=zero-shot2026.0457.60.4240.4241
DeepSeek-V3.1Type=Open-weight, Evaluation Protocol=zero-shot2026.0456.70.4330.4331
MiniMax-M2.5Type=Open-weight, Evaluation Protocol=zero-shot2026.0447.60.4980.4950.974