Qwen3.7-Max
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
coding_agent
|
82.15%
|
18.08.2026 |
#21/44
better than 53%
|
|
NL2Repo-Bench
coding_agent
|
47.67%
|
18.08.2026 |
#15/23
better than 36%
|
|
FrontierSWE
coding_agent
|
19.76%
|
18.08.2026 |
#9/12
better than 27%
|
|
MLS-Bench-Lite
coding_agent
|
21.55%
|
18.08.2026 |
#8/9
better than 12%
|
|
PaperBench
coding_agent
|
54.81%
|
18.08.2026 |
#5/10
better than 56%
|
|
AndroidBench
coding_agent
|
56.50
|
18.08.2026 |
#5/5
better than 0%
|
|
QwenSWEBench
coding_agent
|
38.11%
|
18.08.2026 |
#7/9
better than 25%
|
|
QwenQoderBench
coding_agent
|
36.80
|
18.08.2026 |
#5/5
better than 0%
|
|
QwenReactBench
coding_agent
|
1538.00
|
18.08.2026 |
#5/5
better than 0%
|
|
QwenSVGBench
coding_agent
|
1499.00
|
18.08.2026 |
#5/5
better than 0%
|
|
CoWorkBench
general_agent
|
63.31%
|
18.08.2026 |
#10/12
better than 18%
|
|
WorkSpaceBench
general_agent
|
19.05%
|
18.08.2026 |
#9/11
better than 20%
|
|
JobBench
general_agent
|
20.56%
|
18.08.2026 |
#17/19
better than 11%
|
|
SkillsBench
general_agent
|
70.07%
|
18.08.2026 |
#5/9
better than 50%
|
|
Toolathlon Verified
general_agent
|
43.71%
|
18.08.2026 |
#24/35
better than 32%
|
|
WideSearch
general_agent
|
78.28%
|
18.08.2026 |
#11/24
better than 57%
|
|
GPQA Diamond
stem_reasoning
|
91.87%
|
17.06.2026 |
#29/80
better than 65%
|
|
IFBench
instruction_following
|
91.71%
|
18.08.2026 |
#11/42
better than 73%
|
|
$OneMillion-Bench
general_capabilities
|
9.89%
|
18.08.2026 |
#10/11
better than 10%
|
|
HealthBench
general_capabilities
|
67.80%
|
18.08.2026 |
#4/6
better than 40%
|
|
PLawBench
general_capabilities
|
58.90
|
18.08.2026 |
#5/5
better than 0%
|
|
PRBench-Legal
general_capabilities
|
48.50
|
18.08.2026 |
#5/5
better than 0%
|
|
PRBench-Finance
general_capabilities
|
46.80
|
18.08.2026 |
#5/5
better than 0%
|
|
MRCR v2 256K (8-needle)
long_context
|
33.02%
|
18.08.2026 |
#3/4
better than 33%
|
|
LongBench v2
long_context
|
91.40%
|
18.08.2026 |
#4/22
better than 86%
|
|
Agents' Last Exam
general_agent
|
3.68%
|
18.08.2026 |
#28/29
better than 4%
|
|
CritPt (no tools)
stem_reasoning
|
40.38%
|
17.06.2026 |
#13/21
better than 40%
|
|
AIME 26
stem_reasoning
|
97.19%
|
17.06.2026 |
#9/45
better than 82%
|
|
HMMT Nov 25
stem_reasoning
|
92.39%
|
17.06.2026 |
#3/20
better than 89%
|
|
HMMT Feb 26
stem_reasoning
|
99.22%
|
17.06.2026 |
#2/44
better than 98%
|
|
IMOAnswerBench
stem_reasoning
|
95.74%
|
17.06.2026 |
#5/30
better than 86%
|
|
NL2Repo
coding_agent
|
56.77%
|
17.06.2026 |
#17/41
better than 60%
|
|
Terminal-Bench 2.1 (Terminus-2)
coding_agent
|
79.65%
|
17.06.2026 |
#15/44
better than 67%
|
|
Humanity's Last Exam
stem_reasoning
|
74.43%
|
17.06.2026 |
#16/71
better than 77%
|
|
HLE (with tools)
stem_reasoning
|
70.59%
|
17.06.2026 |
#20/49
better than 60%
|
|
MCP-Atlas
general_agent
|
83.29%
|
17.06.2026 |
#12/54
better than 79%
|
|
DeepSWE 1.1
coding_agent
|
23.18%
|
17.06.2026 |
#27/34
better than 18%
|
|
Automation-Bench
general_agent
|
6.54%
|
18.08.2026 |
#24/27
better than 12%
|
|
SWE-bench Pro
coding_agent
|
67.56%
|
17.06.2026 |
#16/77
better than 80%
|
What is a good Terminal Bench 2.1 score? What is a good NL2Repo-Bench score? What is a good FrontierSWE score?
No comments yet
Be the first to share your thoughts!