Model
Qwen3.5 35B A3B
Alibaba · open weights
Knowledge & Reasoning
Knowledge & ReasoningCoding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Closed-loop evaluation benchmark for embedded coding agents | 26.7 | pass_rate | N/A | Independent | medium | arxiv.org |
| Mobility Data Engineering Benchmark | 77.3 | success_rate | N/A | Independent | medium | arxiv.org |
| SciCode | 29.3 | score | N/A | Independent | medium | artificialanalysis.ai |
Agentic / Tool Use
Agentic / Tool UseMultimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| EgoGears | 37.4 | accuracy | N/A | Independent | medium | arxiv.org |
| Game2Real-Bench | 45.0 | accuracy | N/A | Independent | medium | arxiv.org |
| VisualTrust | 91.3 | accuracy | N/A | Independent | medium | arxiv.org |
Multilingual
MultilingualReproduced by the community
Loading community runs…