Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-round coreference resolution on MRCR
Loading...
81.6
2-Needle Score
DeepSeek-V3.2-Thinking
45.3248
54.7424
64.16
73.5776
May 21, 2026
2-Needle Score
4-Needle Score
Overall Score
Updated 2mo ago
Evaluation Results
Method
Method
Links
2-Needle Score
4-Needle Score
Overall Score
DeepSeek-V3.2-Thinking
2026.05
81.6
60.32
71.01
Qwen3-30B-A3B-Thinking + ACC
2026.05
76.9
59.57
68.28
Qwen3-235B-A22B-Thinking
2026.05
74.98
59.96
67.51
GPT-5.1-Thinking
2026.05
73.75
47.93
60.91
GLM-4.6-Thinking
2026.05
73.63
55.33
64.53
Kimi-K2-Thinking
2026.05
68.01
47.96
58.05
Qwen3-30B-A3B-Thinking
2026.05
61.84
38.41
50.19
GPT-OSS-120B
2026.05
46.72
29.16
38
Feedback
Search any
task
Search any
task