Qwen3.5-9B
Qwen Team (Alibaba Cloud)
Parameters
—
Architecture
—
Released
—
License
—
About
No detailed description available for this model.
Benchmark Scores
| Benchmark | Score | Date |
|---|---|---|
|
Terminal-Bench 2.1 (Terminus-2)
coding_agent
|
0.44%
|
25.06.2026 |
|
Terminal-Bench 2.1 (Claude Code)
coding_agent
|
18.90
|
25.06.2026 |
|
SWE-bench Verified
coding_agent
|
60.44%
|
25.06.2026 |
|
NL2Repo
coding_agent
|
9.08%
|
25.06.2026 |
|
Claw-Eval Avg
coding_agent
|
63.36%
|
25.06.2026 |
|
SWE Atlas - QnA
coding_agent
|
9.20
|
25.06.2026 |
|
SWE Atlas - RF
coding_agent
|
4.30
|
25.06.2026 |
|
SWE Atlas - TW
coding_agent
|
4.40
|
25.06.2026 |
|
VITA-Bench
general_agent
|
29.02%
|
— |
|
BFCL-V4
general_agent
|
85.48%
|
— |
|
TAU2-Bench
general_agent
|
77.78%
|
— |
|
TAU3-Bench
general_agent
|
11.96%
|
— |
|
MCP-Atlas
general_agent
|
47.61%
|
— |
|
MCPMark
general_agent
|
12.04%
|
— |
|
Workspace Bench
|
75.74%
|
— |
|
BrowseComp
general_agent
|
5.90%
|
— |
|
SciCode
|
78.99%
|
— |
|
Gaokao 2026
|
100.00%
|
— |
|
AIME 26
stem_reasoning
|
85.97%
|
— |
|
HMMT Feb 26
stem_reasoning
|
65.16%
|
— |
|
IMOAnswerBench
stem_reasoning
|
67.05%
|
— |
|
IFBench
instruction_following
|
69.55%
|
— |
|
AA-LCR
long_context
|
78.75%
|
— |
|
Humanity's Last Exam
stem_reasoning
|
23.11%
|
— |
|
GPQA
reasoning
|
100.00%
|
— |
|
SWE-bench Pro
coding_agent
|
42.25%
|
25.06.2026 |
|
SWE-bench Multilingual
coding_agent
|
45.33%
|
25.06.2026 |
|
IFEval
instruction_following
|
94.19%
|
— |