qwen3.6-35b-a3b
Published evals
Vendor-card figures for this base model. Not measured on this Spark.
- SWE-bench Verified
- 73.4% Qwen model card ↗ 2026-04-21 Vendor figure; internal agent scaffold (bash + file-edit).
- Terminal-Bench 2.0
- 51.5% Qwen launch blog ↗ 2026-04-14 Vendor figure on the 35B-A3B launch post.
- SWE-bench Pro
- 49.5% Qwen launch blog ↗ 2026-04-14
Independent board on Artificial Analysis ↗ — we do not copy their scores.
Recipe
- Profile
- qwen-qwen3-6-35b-a3b-dflash-eugr
- Engine
- vLLM
- Served as
- qwen3.6-35b-a3b-dflash
- Draft
- DFlash · n15
Run on your Spark
single node
shell
spark inference up qwen-qwen3-6-35b-a3b-dflash-eugr
Bench notes
Overnight full-coverage failed after retries: failed:qwen-qwen3-6-35b-a3b-dflash-eugr