‹ PublicAI Index
The LLM benchmark aggregator.
Qwen3.8 Flash Next
Alibaba
Strongest in Instruction following (#5 of 62), weakest in Reasoning (#120 of 195). Above par in 6 of 9 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5.2 and Muse Wonder Full and ahead of Grok 4.5 and Gemini 3.6 Flash.
§ 1 · Profile
What it is good at
Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.
Agents59.8−6.6#15/2982/6
Knowledge work65.7−5#14/2082/2
Coding54.8−11.4#38/1791/6
Agentic coding55.3−11.6#38/1731/5
Core abilities54.2−11.1#56/1991/4
Instruction following66.2−7.6#5/621/1
Language45.4−21.2#45/621/1
Reasoning47−18.4#120/1951/5
Mathematics45.5−18.3#106/1521/2
§ 2 · Head to head
What it beats, and what beats it
The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for Qwen3.8 Flash Next, left for the other.
§ 3 · Sources
Where the numbers come from
3 publications, 10 figures. Every one links to the page it was read from.
GDPval-AA 1636
AA-Briefcase 1574
LiveBench 1.0 76.2LiveBench 1.0 · Reasoning 87.4LiveBench 1.0 · Coding 72.6LiveBench 1.0 · Agentic Coding 61.6LiveBench 1.0 · Mathematics 85.8LiveBench 1.0 · Data Analysis 74.2LiveBench 1.0 · Language 74.6LiveBench 1.0 · Instruction Following 77.1
Badge
[](https://publicai.io/model-index/m/qwen3-8-flash-next)