Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Qwen3.8 Max

Alibaba

Strongest in Knowledge work (#5 of 178), weakest in Toxicity avoidance (#185 of 272). Above par in 26 of 28 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 5.5 and Claude Fable 5 and ahead of GPT-6 Sol and Gemini 3.8 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.

Agents65#6/268
Knowledge work69.5#5/178
Core abilities58.7#13/204
Instruction following60.9#12/57
General intelligence61.6#15/204
Data analysis58.4#17/57
Language50.8#29/57
Knowledge57.7#21/138
Academic knowledge59.2#18/123
Human preference64.6#22/342
Human preference64.6#22/342
Professional56.1#27/168
Legal59.8#14/151
Finance56.3#32/151
Medical52.4#68/140
Reasoning55.9#31/178
Science62.3#6/122
Reasoning56#37/140
Mathematics52.8#67/140
Coding53.5#42/165
Agentic coding57.1#24/157
Code generation40.8#59/77
Safety53.1#100/337
Secure code63.9#20/274
Harm refusal52.4#120/300
Fairness48.3#136/300
Jailbreak resistance53.2#142/272
Toxicity avoidance51.1#185/272

§ 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 Max, left for the other.

Mistral Medium 3.5won 17 · lost 0
Grok Build 0.1won 19 · lost 0
Mistral Smallwon 19 · lost 0
Mistral Large 3won 19 · lost 0
Grok 3won 20 · lost 0
Grok 4.3won 28 · lost 0
DeepSeek V3won 24 · lost 1
Command Awon 21 · lost 1
Qwen3.8 27Bwon 21 · lost 1
Qwen3.6 Pluswon 21 · lost 1
GPT-5.4 Miniwon 21 · lost 1
Gemini 3.5 Flash Litewon 21 · lost 1
Grok 4.1 Fastwon 20 · lost 1
Ling 3.0 Flashwon 17 · lost 1
Gemini 3.1 Flash Litewon 17 · lost 1
Mistral Largewon 16 · lost 1
Grok 4 Fastwon 16 · lost 1
Gemini 2.5 Flashwon 22 · lost 2
GPT-5.4 Nanowon 21 · lost 2
Kimi K2won 21 · lost 2
Mimo V2.5 Prowon 21 · lost 2
Llama 4 Scout Instructwon 20 · lost 2
Gemini 2.0 Flashwon 20 · lost 2
Gemma 4 31Bwon 19 · lost 2
Kimi K2.7 Codewon 17 · lost 2
DeepSeek V4 Flashwon 25 · lost 3
Kimi K2.6won 25 · lost 3
GLM-5.2won 25 · lost 3
Gemini 2.5 Flash Litewon 15 · lost 2
GLM-5won 15 · lost 2
GPT-4o Miniwon 21 · lost 3
GPT-4.1 Nanowon 21 · lost 3
DeepSeek V3.2won 21 · lost 3
Grok 4won 20 · lost 3
GLM-4.6won 20 · lost 3
GPT OSS 20Bwon 18 · lost 3
MiniMax M3won 24 · lost 4
Claude Sonnet 4.6won 22 · lost 4
GPT-4.1 Miniwon 20 · lost 4
Kimi K2.5won 20 · lost 4
Qwen3.7 Maxwon 23 · lost 5
Kimi K2 Thinkingwon 16 · lost 4
GPT-6 Lunawon 20 · lost 5
Gemini 2.5 Prowon 20 · lost 5
DeepSeek R1won 19 · lost 5
GLM-4.5won 15 · lost 4
GLM-5.3 Flashwon 22 · lost 6
Gemini 1.5 Prowon 14 · lost 4
GLM-5.1won 17 · lost 5
Claude Sonnet 4won 19 · lost 6
Claude 3.5 Haikuwon 15 · lost 5
GPT OSS 120Bwon 18 · lost 6
Claude Haiku 4.5won 18 · lost 6
Inklingwon 21 · lost 7
DeepSeek V4 Prowon 21 · lost 7
Claude Opus 4.5won 16 · lost 6
GPT-4owon 15 · lost 6
GPT-5.6 Lunawon 20 · lost 8
O4 Miniwon 17 · lost 7
Claude Sonnet 4.5won 17 · lost 7
Claude 3.5 Sonnetwon 14 · lost 6
GPT-4.1won 16 · lost 7
Qwen3 235B A22B Instructwon 16 · lost 7
Gemini 3.5 Flashwon 19 · lost 9
GPT-5 Nanowon 14 · lost 7
Claude 3.7 Sonnetwon 14 · lost 7
MiniMax M2.7won 14 · lost 7
GPT-5 Miniwon 16 · lost 8
Claude Opus 4won 15 · lost 8
O1won 13 · lost 7
Grok 4.5won 18 · lost 10
Gemini 3.6 Flashwon 18 · lost 10
GPT-5won 15 · lost 9
O3 Miniwon 14 · lost 9
GLM-5.3won 13 · lost 9
O3won 14 · lost 10
DeepSeek V4.1 Flashwon 12 · lost 9
Claude Sonnet 5won 16 · lost 12
GPT-5.4won 16 · lost 12
GPT-5.2won 15 · lost 12
GPT-5.1won 12 · lost 10
Gemini 3.8 Flashwon 15 · lost 13
GPT-6 Solwon 13 · lost 12
Muse Spark 1.2won 10 · lost 11
GPT-5.6 Terrawon 13 · lost 15
Muse Spark 1.1won 13 · lost 15
Gemini 3 Prowon 9 · lost 11
Gemini 3.1 Prowon 10 · lost 13
Mimo V2.6 Prowon 8 · lost 11
Claude Opus 4.6won 10 · lost 14
GPT-6 Astrawon 8 · lost 12
Claude Opus 4.7won 11 · lost 17
Grok 4.7won 9 · lost 16
Claude Opus 4.8won 10 · lost 18
Grok 4.6won 9 · lost 19
GPT-5.5won 9 · lost 19
Gemini 3.7 Flashwon 7 · lost 15
Kimi K3won 7 · lost 15
GPT-5.6 Solwon 8 · lost 20
Claude Opus 5won 6 · lost 22
Muse Spark 1.3won 2 · lost 16
Claude Fable 5.1won 2 · lost 20
Claude Fable 5won 2 · lost 20
Claude Opus 5.5won 2 · lost 23

§ 3 · Sources

Where the numbers come from

7 publications, 33 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-09-26
LMArena Text 1479
Artificial Analysis ↗1 measureread 2026-09-26
Artificial Analysis Intelligence Index 45
GDPval-AA ↗1 measureread 2026-09-26
GDPval-AA 1668
AA-Briefcase ↗1 measureread 2026-09-26
AA-Briefcase 1626
LiveBench ↗8 measuresread 2026-09-26
LiveBench 78.5LiveBench · Reasoning 88.2LiveBench · Coding 72.9LiveBench · Agentic Coding 64.6LiveBench · Mathematics 91.3LiveBench · Data Analysis 78.4LiveBench · Language 79.7LiveBench · Instruction Following 74.1
Vals.ai ↗15 measuresread 2026-09-26
Vals · Legal Research Bench 47.6%Vals · LegalBench 83.61%Vals · Harvey Legal Agent Benchmark 10.42%Vals · Finance Agent 50.59%Vals · CorpFin 65.85%Vals · TaxEval 75.55%Vals · MortgageTax 63.99%Vals · MedCode 40.67%Vals · MedScribe 84.95%Vals · SWE-bench Verified 85.6% (Mini-SWE-agent)Vals · Vibe Code Bench 64.7% (OpenHands)Vals · Code Migration 23.96%Vals · GPQA Diamond 93.69%Vals · MMLU Pro 88.6%Vals · ProofBench 58%
Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-09-26
Enkrypt · Jailbreak risk 10.1%Enkrypt · Harmful content risk 0.6%Enkrypt · CBRN risk 26%Enkrypt · Toxicity risk 5.5%Enkrypt · Bias risk 80.4%Enkrypt · Insecure code risk 5.3%

Badge

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