Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Qwen3.8 Flash Next

Alibaba

Strongest in Instruction following (#5 of 57), weakest in Mathematics (#97 of 140). Above par in 8 of 13 scopes. Among the models it meets almost everywhere, it finishes behind Muse Spark 1.3 and Claude Fable 5.1 and ahead of DeepSeek V4 Flash Vision and Gemini 3.5 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.

Agents64.2#8/268
Knowledge work68.4#7/178
Core abilities54.7#50/204
Instruction following66.1#5/57
Data analysis51.3#32/57
General intelligence57.3#42/204
Language41.2#43/57
Coding49.9#77/165
Agentic coding55.9#33/157
Code generation40.2#60/77
Reasoning49.8#92/178
Reasoning54.9#42/140
Mathematics45#97/140

§ 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.

Mistral Medium 3.5won 8 · lost 0
Mercury 2.5won 8 · lost 0
Mimo V2.5 Prowon 8 · lost 0
GPT-4.1 Nanowon 9 · lost 0
Mistral Large 3won 9 · lost 0
GPT-4o Miniwon 10 · lost 0
Qwen3.6 27Bwon 13 · lost 0
Grok 4.3won 13 · lost 0
GPT-5.4 Miniwon 13 · lost 0
Grok Build 0.1won 13 · lost 0
Inklingwon 13 · lost 0
Gemini 3.5 Flash Litewon 12 · lost 1
DeepSeek V3won 9 · lost 1
Claude Haiku 4.5won 8 · lost 1
GPT OSS 120Bwon 8 · lost 1
GPT-4.1 Miniwon 8 · lost 1
GPT-4.1won 7 · lost 1
GPT-5.4 Nanowon 11 · lost 2
Kimi K2.7 Codewon 11 · lost 2
Kimi K2.6won 11 · lost 2
MiniMax M3won 11 · lost 2
Ox Alphawon 9 · lost 2
Granite 4.2 3Bwon 7 · lost 2
Nemotron 3 Ultrawon 7 · lost 2
DeepSeek V3.2won 7 · lost 2
Claude Sonnet 4.5won 7 · lost 2
Qwen3.6 Pluswon 10 · lost 3
Qwen3.8 27Bwon 10 · lost 3
Qwen3.6 35B A3Bwon 6 · lost 2
GLM-4.6won 6 · lost 2
Kimi K2won 6 · lost 2
Gemma 4 31Bwon 6 · lost 2
GLM-5.3 Flashwon 9 · lost 4
Qwen3.7 Maxwon 9 · lost 4
Granite 4.2 8Bwon 6 · lost 3
K2 Horizon 3.7Bwon 6 · lost 3
K2 Horizon 7Bwon 6 · lost 3
Gemini 2.5 Flashwon 6 · lost 3
GPT-5.2 Codexwon 7 · lost 4
O3 Miniwon 5 · lost 3
K2 Horizon 0.9Bwon 5 · lost 3
Gemma 4 12Bwon 5 · lost 3
Qwen3.5 9Bwon 5 · lost 3
K2 Horizon 375B A23Bwon 5 · lost 3
Gemini 3.1 Flash Litewon 5 · lost 3
GPT-6 Lunawon 8 · lost 5
GPT-5.6 Lunawon 8 · lost 5
GLM-5.2won 8 · lost 5
Gemini 3.6 Flashwon 8 · lost 5
Claude Opus 4.5won 7 · lost 5
GPT-5 Miniwon 5 · lost 4
Kimi K2.5won 5 · lost 4
Claude Sonnet 4.6won 7 · lost 6
Muse Spark 1.1won 7 · lost 6
Gemini 3.5 Flashwon 7 · lost 6
Gemini 2.5 Prowon 5 · lost 5
Claude Sonnet 4won 5 · lost 5
GPT-5.2won 6 · lost 6
Claude Sonnet 5won 6 · lost 7
DeepSeek V4 Flashwon 6 · lost 7
Grok 4.5won 6 · lost 7
Union Alphawon 5 · lost 6
O4 Miniwon 4 · lost 5
GPT-5won 4 · lost 5
DeepSeek R1won 4 · lost 6
GLM-5.3won 5 · lost 8
Claude Opus 4.8won 5 · lost 8
DeepSeek V4 Prowon 5 · lost 8
Gemini 3.8 Flashwon 5 · lost 8
GPT-5.4won 5 · lost 8
Gemini 3.7 Flashwon 5 · lost 8
Gemini 3.1 Prowon 5 · lost 8
Grok 4won 3 · lost 5
Claude Opus 4won 3 · lost 5
Gemini 3 Prowon 3 · lost 5
Claude Opus 4.6won 4 · lost 7
O3won 3 · lost 6
Muse Spark 1.2won 4 · lost 9
Claude Opus 4.7won 4 · lost 9
GPT-5.6 Terrawon 4 · lost 9
Grok 4.6won 4 · lost 9
Mimo V2.6 Prowon 2 · lost 6
DeepSeek V4.1 Flashwon 3 · lost 10
Kimi K3won 3 · lost 10
GPT-6 Solwon 3 · lost 10
GPT-5.6 Solwon 3 · lost 10
GPT-5.5won 3 · lost 10
GPT-6 Astrawon 3 · lost 10
Grok 4.7won 2 · lost 11
Claude Fable 5won 2 · lost 11
Claude Opus 5won 1 · lost 12
Qwen3.8 Maxwon 1 · lost 12
Claude Opus 5.5won 1 · lost 12
Claude Fable 5.1won 1 · lost 12
Muse Spark 1.3won 0 · lost 13

§ 3 · Sources

Where the numbers come from

4 publications, 11 figures. Every one links to the page it was read from.

Artificial Analysis ↗1 measureread 2026-09-26
Artificial Analysis Intelligence Index 40
GDPval-AA ↗1 measureread 2026-09-26
GDPval-AA 1612
AA-Briefcase ↗1 measureread 2026-09-26
AA-Briefcase 1588
LiveBench ↗8 measuresread 2026-09-26
LiveBench 76.2LiveBench · Reasoning 87.4LiveBench · Coding 72.6LiveBench · Agentic Coding 61.6LiveBench · Mathematics 85.8LiveBench · Data Analysis 74.2LiveBench · Language 74.6LiveBench · Instruction Following 77.1

Badge

PublicAI Index badge for Qwen3.8 Flash Next[![PublicAI Index](https://publicai.io/model-index/badge?model=qwen3-8-flash-next)](https://publicai.io/model-index/m/qwen3-8-flash-next)