List your company

Memory Question Answering on ATM-Bench

86QS ScoreClaude Opus 4.5
32.75246.57660.474.224Mar 2, 2026

Evaluation results

MethodLinks
Claude Opus 4.5Retriever=Oracle, Reasoning Effort=medium2026.0386
GPT-5Retriever=Oracle, Reasoning Effort=medium2026.0385.3
Claude Sonnet 4.5Retriever=Oracle, Reasoning Effort=medium2026.0383.3
Gemini 2.5 ProRetriever=Oracle, Reasoning Effort=medium2026.0378.6
Qwen3-VL-8BRetriever=Oracle, Reasoning Effort=medium, Variant=Instruct2026.0377.8
Gemini 2.5 FlashRetriever=Oracle, Reasoning Effort=medium2026.0376.9
Qwen3-VL-2BRetriever=Oracle, Reasoning Effort=medium, Variant=Instruct2026.0334.8