List your company

Open-Domain QA on SituatedQA Nq=300

44.6AccuracyGemini3Pro
19.74426.19732.6539.103Feb 12, 2026

Evaluation results

MethodLinks
Gemini3ProNq=3002026.0244.60.5840.5940.68561.612.748.9
KimiK2Nq=3002026.0237.30.6310.590.75264.313.850.5
PooledNq=15002026.0231.80.5670.5730.64146.813.333.5
Claude4.5SNq=3002026.0230.70.5020.5690.49544.419.524.9
GPT-OSSNq=3002026.0225.70.660.6340.75844.43.141.3
Qwen3Nq=3002026.0220.70.4940.5210.56132.816.316.5