Single attempt vs memento, by model
Both use the detailed prompt. Counts are successes / runs; whiskers are Wilson 95% intervals.
0
20
40
60
80
100
inference setup success rate (%)
Qwen3-Coder-30B-A3B
Gemma4-26B-A4B
Qwen3.5-9B (thinking off)
3/13
16/26
10/21
14/22
11/15
10/29
single attempt
memento chain