Loading timeline…
Loading timeline…
Every recorded change for this model by Alibaba Group, newest first. Back to the entity page →
7 events
New model: qwen3-4b-2507-instruct-reasoning (Alibaba Group)
qwen3-4b-2507-instruct-reasoning scores 1.52% on Terminal-Bench
qwen3-4b-2507-instruct-reasoning scores 25.44% on τ²-bench
qwen3-4b-2507-instruct-reasoning scores 49.8% on IFBench
qwen3-4b-2507-instruct-reasoning scores 6.16% on Humanity's Last Exam
qwen3-4b-2507-instruct-reasoning scores 66.67% on GPQA
qwen3-4b-2507-instruct-reasoning scores 8.8 on Artificial Analysis Intelligence Index
Showing up to 400 events. Narrow by year or category, or use the changes feed for cursor-paged history. Times are UTC.