Request a Pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Qwen3.8 Flash Next

Alibaba

Strongest in Instruction following (#5 of 62), weakest in Reasoning (#119 of 195). Above par in 7 of 10 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5.2 and Muse Wonder Full and ahead of Gemini 3.6 Flash and GPT-5.2.

§ 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#14/298
Knowledge work65.7#14/208
Coding54.8#38/179
Agentic coding55.3#36/173
Core abilities53.8#59/200
Instruction following66.2#5/62
Language45.4#45/62
General intelligence51.4#76/180
Reasoning47#119/195
Mathematics45.5#106/152

§ 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.

GPT-4owon 6 · lost 0
Mercury 2.5won 6 · lost 0
Claude 3.5 Haikuwon 6 · lost 0
MiMo V2.5won 6 · lost 0
MiMo V2.5 Prowon 6 · lost 0
Smaug Nemotron 3.5won 6 · lost 0
Llama 4 Scout Instructwon 6 · lost 0
Gemini 2.0 Flashwon 6 · lost 0
Gemma 3 27B ITwon 6 · lost 0
Qwen3 32Bwon 6 · lost 0
Gemma 4 31Bwon 7 · lost 0
Ox Alphawon 7 · lost 0
Nemotron 3.5 Super VLwon 7 · lost 0
Muse Spark Openwon 7 · lost 0
Command Awon 7 · lost 0
GPT-4.1won 7 · lost 0
GPT-4o miniwon 8 · lost 0
Mistral Medium 3.5won 8 · lost 0
GPT-4.1 nanowon 8 · lost 0
Step 5won 8 · lost 0
Inkling Smallwon 8 · lost 0
Beam 1.0won 8 · lost 0
Mistral Large 3won 8 · lost 0
Qwen3.6 27Bwon 9 · lost 0
Grok Build 0.1won 9 · lost 0
NVIDIA Nemotron 3.5 Lightning 30B A3Bwon 10 · lost 0
Gemini 3.5 Flash-Litewon 10 · lost 0
Qwen3.8 27Bwon 10 · lost 0
MiniMax M3won 9 · lost 1
Mistral Large 4won 9 · lost 1
GLM-5.3 Flashwon 9 · lost 1
Kimi K2.7 Codewon 8 · lost 1
Grok 4.3won 8 · lost 1
GPT-4.1 miniwon 7 · lost 1
DeepSeek V3won 7 · lost 1
Llama 4 Maverick Instructwon 7 · lost 1
MiniMax M3.1 Flashwon 6 · lost 1
Kimi K2won 6 · lost 1
Qwen3 235B A22B Instructwon 6 · lost 1
GPT-5.4 miniwon 8 · lost 2
GPT-5.4 nanowon 8 · lost 2
GPT-5.6 Lunawon 8 · lost 2
GPT-6 Lunawon 8 · lost 2
Inklingwon 8 · lost 2
NVIDIA Nemotron 3 Ultra 550B A55Bwon 8 · lost 2
Kimi K2.6won 7 · lost 2
Muse Spark 1.1won 7 · lost 2
GPT OSS 120Bwon 6 · lost 2
GLM-4.6won 6 · lost 2
DeepSeek V3.2won 6 · lost 2
GPT-5.2 Codexwon 5 · lost 2
Gemini 2.5 Flashwon 5 · lost 2
DeepSeek V4 Flashwon 7 · lost 3
O3 Miniwon 4 · lost 2
Muse Sparkwon 4 · lost 2
MiniMax M2.7won 4 · lost 2
GPT-5.1won 4 · lost 2
GLM-4.7won 4 · lost 2
GLM-5.1won 4 · lost 2
Claude Haiku 4.5won 4 · lost 2
GPT OSS 20Bwon 4 · lost 2
MiniMax M2.5won 4 · lost 2
Grok 3won 4 · lost 2
Qwen3.6 Pluswon 6 · lost 3
Claude Sonnet 5won 6 · lost 3
Claude Sonnet 4.6won 6 · lost 3
Qwen3.7 Maxwon 6 · lost 3
Gemini 3.5 Flashwon 6 · lost 3
MiMo V2.6 Prowon 5 · lost 3
Claude Sonnet 4.5won 5 · lost 3
GLM-5.2won 6 · lost 4
Gemini 3.8 Flashwon 6 · lost 4
Kimi K3won 6 · lost 4
GPT-5.2won 5 · lost 4
Gemini 3.6 Flashwon 5 · lost 4
Grok 3 Miniwon 3 · lost 3
Claude Opus 4won 3 · lost 3
MiMo V2.6 Flashwon 4 · lost 4
Gemini 3.1 Flash-Litewon 4 · lost 4
Gemini 2.5 Prowon 4 · lost 4
GPT-5 miniwon 4 · lost 4
GPT-5won 4 · lost 4
Claude Sonnet 4won 4 · lost 4
Kimi K2.5won 4 · lost 4
Claude Haiku 5.5won 5 · lost 5
DeepSeek V4 Prowon 5 · lost 5
GPT-5.6 Terrawon 5 · lost 5
Grok 4.6won 5 · lost 5
Qwen3.8 Maxwon 5 · lost 5
Claude Opus 4.7won 5 · lost 5
GPT-5.4won 5 · lost 5
Grok 4.5won 5 · lost 5
DeepSeek V4 Flash Visionwon 4 · lost 5
Claude Opus 4.5won 4 · lost 5
Gemini 3.1 Prowon 4 · lost 5
Gemini 3.7 Flashwon 4 · lost 5
Inkling 2 Smallwon 3 · lost 4
Muse Emberwon 3 · lost 4
Grok 4won 3 · lost 4
GLM-5.3won 4 · lost 6
Claude Opus 4.6won 3 · lost 5
DeepSeek R1won 3 · lost 5
Kimi K3.1 Prowon 3 · lost 5
Kimi K2 Thinkingwon 2 · lost 4
Grok 4 Fastwon 2 · lost 4
Qwen3 Maxwon 2 · lost 4
Grok 4.20won 2 · lost 4
GLM-5won 2 · lost 4
GPT-6 Solwon 3 · lost 6
Muse Spark 1.2won 3 · lost 6
Grok 4.7won 3 · lost 7
GPT-5.6 Solwon 3 · lost 7
Claude Opus 4.8won 3 · lost 7
GPT-5.5won 3 · lost 7
Gemini 3 Prowon 2 · lost 5
GPT-6.1 Terrawon 2 · lost 5
Claude Opus 5won 2 · lost 7
DeepSeek V4.1 Flashwon 2 · lost 8
Muse Wonderwon 2 · lost 8
GPT-6.1 Solwon 2 · lost 8
GPT-6 Astrawon 2 · lost 8
Claude Fable 5won 2 · lost 8
O4 Miniwon 1 · lost 6
O3won 1 · lost 6
Gemini 4 Argonwon 1 · lost 7
Claude Sonnet 5.5won 1 · lost 9
Muse Spark 1.3won 1 · lost 9
Claude Opus 5.5won 1 · lost 9
Claude Fable 5.1won 1 · lost 9
Gemini 4 Carbonwon 0 · lost 7
Muse Wonder Fullwon 0 · lost 8
Claude Fable 5.2won 0 · lost 8

§ 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 2026-11-11
Artificial Analysis Intelligence Index 29
GDPval-AA ↗1 measureread 2026-11-11
GDPval-AA 1636
AA-Briefcase ↗1 measureread 2026-11-11
AA-Briefcase 1573
LiveBench 1.0 ↗8 measuresread 2026-11-11
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

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)