Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Long-context Question Answering on NovelQA
Loading...
84.85
Accuracy
StateLM-14B-RL
13.6412
32.1281
50.615
69.1019
Feb 12, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
StateLM-14B-RL
Context=32K
2026.02
84.85
StateLM-8B-RL
Context=32K
2026.02
84.15
StateLM-14B
Context=32K
2026.02
84.15
StateLM-8B
Context=32K
2026.02
83.84
Qwen3-235B (w/ Pensieve)
Context=256K
2026.02
80.71
StateLM-4B
Context=32K
2026.02
79.57
RL-MemoryAgent-14B
Context=32K
2026.02
78.86
Qwen3-14B
Context=128K
2026.02
77.94
Qwen3-8B
Context=128K
2026.02
65.87
Qwen3-4B
Context=128K
2026.02
65.17
RL-MemoryAgent-7B
Context=32K
2026.02
60.24
ReadAgent-14B
Context=32K
2026.02
23.12
ReadAgent-8B
Context=32K
2026.02
16.38
Feedback
Search any
task
Search any
task