Qwen3.7-Plus
Qwen Team (Alibaba Cloud)
Parameters
—
Architecture
—
Released
—
License
—
About
No detailed description available for this model.
Benchmark Scores
| Benchmark | Score | Date | Standing |
|---|---|---|---|
|
Terminal-Bench 2.1 (Terminus-2)
coding_agent
|
63.42%
|
18.08.2026 |
#25/44
better than 44%
|
|
NL2Repo
coding_agent
|
47.38%
|
18.08.2026 |
#24/41
better than 42%
|
|
GPQA Diamond
stem_reasoning
|
92.44%
|
18.08.2026 |
#27/80
better than 67%
|
|
Humanity's Last Exam
stem_reasoning
|
61.74%
|
18.08.2026 |
#30/71
better than 59%
|
|
IFBench (prompt loose)
instruction_following
|
85.13%
|
18.08.2026 |
#4/14
better than 69%
|
|
OmniDocBench 1.5
document_understanding
|
99.78%
|
18.08.2026 |
#2/26
better than 96%
|
|
CharXiv (RQ)
document_understanding
|
78.26%
|
18.08.2026 |
#3/34
better than 94%
|
|
RealWorldQA
vision_language
|
96.28%
|
18.08.2026 |
#2/23
better than 95%
|
|
AndroidWorld
general_agent
|
86.49%
|
18.08.2026 |
#3/13
better than 83%
|
|
Claw-Eval Avg
coding_agent
|
72.02%
|
18.08.2026 |
#20/40
better than 51%
|
|
QwenSWEBench
coding_agent
|
26.76%
|
18.08.2026 |
#8/9
better than 12%
|
|
CoWorkBench
general_agent
|
64.94%
|
18.08.2026 |
#9/12
better than 27%
|
|
JobBench
general_agent
|
12.55%
|
18.08.2026 |
#18/19
better than 6%
|
|
OSWorld-Verified
general_agent
|
76.63%
|
18.08.2026 |
#9/25
better than 67%
|
|
WebArena-Verified
general_agent
|
75.03%
|
18.08.2026 |
#2/5
better than 75%
|
|
RecreationBench
general_agent
|
1.99%
|
18.08.2026 |
#3/4
better than 33%
|
|
SWE-MM
coding_agent
|
33.33%
|
18.08.2026 |
#2/4
better than 67%
|
|
Vision2Web
vision_language
|
42.10
|
18.08.2026 |
#4/4
better than 0%
|
|
MathVision
vision_language
|
85.52%
|
18.08.2026 |
#4/27
better than 88%
|
|
Agents' Last Exam
general_agent
|
7.98%
|
18.08.2026 |
#27/29
better than 7%
|
|
HLE (with tools)
stem_reasoning
|
37.08%
|
26.08.2026 |
#41/49
better than 17%
|
|
SWE-bench Multilingual
coding_agent
|
83.79%
|
26.08.2026 |
#16/48
better than 66%
|
|
NL2Repo-Bench
coding_agent
|
36.31%
|
26.08.2026 |
#19/23
better than 18%
|
|
Agents' Last Exam (Score)
general_agent
|
33.60
|
26.08.2026 |
#3/3
better than 0%
|
|
Toolathlon Verified
general_agent
|
45.51%
|
26.08.2026 |
#22/35
better than 38%
|
|
OSWorld 2.0 (Binary)
general_agent
|
2.80
|
26.08.2026 |
#8/8
better than 0%
|
|
OSWorld 2.0 (Partial)
general_agent
|
21.50
|
26.08.2026 |
#3/3
better than 0%
|
|
LiveCodeBench v6
stem_reasoning
|
94.68%
|
18.08.2026 |
#10/49
better than 81%
|
|
DeepSWE 1.1
coding_agent
|
18.23%
|
18.08.2026 |
#29/34
better than 15%
|
|
LVBench
video_understanding
|
98.87%
|
26.08.2026 |
#2/12
better than 91%
|
|
ERQA
spatial_intelligence
|
92.60%
|
18.08.2026 |
#2/21
better than 95%
|
|
SWE-bench Pro
coding_agent
|
64.21%
|
18.08.2026 |
#28/77
better than 64%
|
|
IFBench
instruction_following
|
91.71%
|
26.08.2026 |
#11/42
better than 73%
|
|
Claw-Eval Pass^3
coding_agent
|
60.79%
|
18.08.2026 |
#9/21
better than 55%
|
|
BabyVision
vision_language
|
63.93%
|
18.08.2026 |
#9/24
better than 65%
|
What is a good Terminal-Bench 2.1 (Terminus-2) score? What is a good NL2Repo score? What is a good GPQA Diamond score?
No comments yet
Be the first to share your thoughts!