Qwen3.5 2B
Qwen3.5 2B is a small open-weight multimodal model from Alibaba for efficient reasoning, coding, visual understanding, tool use, and JSON output.
- Reasoning
- Vision
- Tool Calling
- Structured Output
Added Aug 16, 2026
Pricing
Auto routing · per 1M tokens- Input
- $0.080
- Output
- $0.16
Specifications
- Context window
- 262.1K
- Max output
- 32.8K
- Parameters
- 2B
Benchmarks
Benchmarks
Sourced from Artificial Analysis.
Intelligence Index
6.2
Coding Index
2.4
Agentic work
T²-Bench Telecom (legacy)
Legacy fallback · Conversational AI agents in dual-control scenarios
81.6%
Better than 72% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
-363 Elo
Better than 3% of models compared
Document reasoning
AA-LCR v1.1
Long context reasoning with updated grading
14.0%
Better than 18% of models compared
Reasoning
HLE
Humanity's Last Exam
5.0%
Better than 27% of models compared
IFBench
Instruction-following benchmark
29.1%
Better than 13% of models compared
Coding
Terminal-Bench Hard (legacy)
Legacy fallback · Agentic coding and terminal use
3.8%
Better than 26% of models compared
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
43.8%
Better than 19% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
14.0%
Better than 17% of models compared
Last updated Oct 14, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…