Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Memory Question Answering on ATM-Bench
Loading...
86
QS Score
Claude Opus 4.5
32.752
46.576
60.4
74.224
Mar 2, 2026
QS Score
Updated 4mo ago
Evaluation Results
Method
Method
Links
QS Score
Claude Opus 4.5
Retriever=Oracle, Reas...
2026.03
86
GPT-5
Retriever=Oracle, Reas...
2026.03
85.3
Claude Sonnet 4.5
Retriever=Oracle, Reas...
2026.03
83.3
Gemini 2.5 Pro
Retriever=Oracle, Reas...
2026.03
78.6
Qwen3-VL-8B
Retriever=Oracle, Reas...
2026.03
77.8
Gemini 2.5 Flash
Retriever=Oracle, Reas...
2026.03
76.9
Qwen3-VL-2B
Retriever=Oracle, Reas...
2026.03
34.8
Feedback
Search any
task
Search any
task