Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

GLM Legal

Z.ai

Strongest in Legal (#8 of 162), weakest in Professional (#19 of 187). Above par in 2 of 2 scopes. Among the models it meets almost everywhere, it finishes behind Gemini 4 Argon and Muse Wonder Full and ahead of GPT-5 and GPT-5.6 Sol.

§ 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.

Professional56.5#19/187
Legal61.4#8/162

§ 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 GLM Legal, left for the other.

NVIDIA Nemotron 3.5 Lightning 30B A3Bwon 2 · lost 0
Command A+won 2 · lost 0
Gemini 1.5 Flashwon 2 · lost 0
Jamba 1.5 Miniwon 2 · lost 0
Llama 4 Scout Instructwon 2 · lost 0
Laguna XS.2won 2 · lost 0
Jamba 1.6 Miniwon 2 · lost 0
Laguna M.1won 2 · lost 0
Mercury 2.5won 2 · lost 0
Mistral Medium 3.5won 2 · lost 0
Jamba 1.6 Largewon 2 · lost 0
GPT-4.1 Nanowon 2 · lost 0
Mixtral 8x7b Instructwon 2 · lost 0
Jamba 1.5 Largewon 2 · lost 0
Llama 4 Maverick Instructwon 2 · lost 0
Mistral Medium 3.1won 2 · lost 0
Gemini 1.5 Prowon 2 · lost 0
Command R Pluswon 2 · lost 0
GPT 3.5won 2 · lost 0
Mistral Small 3.1 24B Instructwon 2 · lost 0
Magistral Small 1.2won 2 · lost 0
Magistral Medium 1.2won 2 · lost 0
GPT-5 Nanowon 2 · lost 0
GPT OSS 20Bwon 2 · lost 0
Claude 3.5 Haikuwon 2 · lost 0
Llama 2 7B Chatwon 2 · lost 0
Command Rwon 2 · lost 0
Llama 2 13B Chatwon 2 · lost 0
Mistral 7B Instructwon 2 · lost 0
Grok 4.20won 2 · lost 0
Claude Haiku 4.5won 2 · lost 0
Gemma 4 31Bwon 2 · lost 0
Mimo V2.5won 2 · lost 0
Ling 3.0 Flash Finwon 2 · lost 0
Llama 2 70B Chatwon 2 · lost 0
NVIDIA Nemotron 3 Ultra 550B A55Bwon 2 · lost 0
GPT-5.4 Nanowon 2 · lost 0
Gemini 2.0 Flashwon 2 · lost 0
DeepSeek V3.1won 2 · lost 0
Ling 3.0 Flashwon 2 · lost 0
MiniMax M2.7won 2 · lost 0
GLM-4.7won 2 · lost 0
Gemini 3.1 Flash Litewon 2 · lost 0
Gemma 2 27B Itwon 2 · lost 0
Gemma 2 9B Itwon 2 · lost 0
Mimo V2.5 Prowon 2 · lost 0
Llama 3.3 70B Instructwon 2 · lost 0
Gemini 2.5 Flash Litewon 2 · lost 0
Qwen3.7 Pluswon 2 · lost 0
Qwen 2.5 Instruct (7B)won 2 · lost 0
O3 Miniwon 2 · lost 0
GPT-5.4 Miniwon 2 · lost 0
Gemini 1.0 Prowon 2 · lost 0
Command Awon 2 · lost 0
Qwen3.6 Pluswon 2 · lost 0
Qwen3.6 Maxwon 2 · lost 0
DeepSeek V3.2won 2 · lost 0
MiniMax M2.1won 2 · lost 0
GPT OSS 120Bwon 2 · lost 0
DeepSeek R1won 2 · lost 0
Trinity Largewon 2 · lost 0
Claude Sonnet 4won 2 · lost 0
DeepSeek V4won 2 · lost 0
Grok 4.3won 2 · lost 0
Grok 4.1 Fastwon 2 · lost 0
GLM-5.1won 2 · lost 0
Kimi K2won 2 · lost 0
DeepSeek V3won 2 · lost 0
Qwen2.5 72B Instructwon 2 · lost 0
GPT-4owon 2 · lost 0
Qwen3 Maxwon 2 · lost 0
Gemini 3.5 Flash Litewon 2 · lost 0
Qwen3.5 Flashwon 2 · lost 0
MiniMax M2.5won 2 · lost 0
GPT-6 Lunawon 2 · lost 0
Step 5won 2 · lost 0
O4 Miniwon 2 · lost 0
Inklingwon 2 · lost 0
Kimi K2.5won 2 · lost 0
Qwen3.7 Maxwon 2 · lost 0
GLM-4.6won 2 · lost 0
GPT-4 Turbowon 2 · lost 0
DeepSeek V4 Flashwon 2 · lost 0
Mistral Large 3won 2 · lost 0
Kimi K2.6won 2 · lost 0
Gemini 3.6 Flashwon 2 · lost 0
Mistral Large 4won 2 · lost 0
Inkling Smallwon 2 · lost 0
Grok 4won 2 · lost 0
Qwen3.6 27Bwon 2 · lost 0
GPT-4.1 Miniwon 2 · lost 0
Qwen3.8 27Bwon 2 · lost 0
GLM-4.5won 2 · lost 0
GPT-5.6 Lunawon 2 · lost 0
GLM-5won 2 · lost 0
Qwen3 235B A22B Instructwon 2 · lost 0
Grok 4 Fastwon 2 · lost 0
Gemini 3.8 Flashwon 2 · lost 0
Claude Opus 4.1won 2 · lost 0
Gemini 3.1 Prowon 2 · lost 0
Gemini 2.5 Flashwon 2 · lost 0
Claude Opus 4won 2 · lost 0
Hy4won 2 · lost 0
Ember 1won 2 · lost 0
Grok 3won 2 · lost 0
DeepSeek V4 Prowon 2 · lost 0
Mimo V2.6 Flashwon 2 · lost 0
MiniMax M3won 2 · lost 0
GLM-5.2won 2 · lost 0
Gemini 3.7 Flashwon 2 · lost 0
Gemini 3 Flashwon 2 · lost 0
Qwen3.8 Maxwon 2 · lost 0
Grok 3 Miniwon 2 · lost 0
O1won 2 · lost 0
Claude 3.7 Sonnetwon 2 · lost 0
GPT-5.6 Terrawon 2 · lost 0
DeepSeek V4.1 Flashwon 2 · lost 0
Kimi K2 Thinkingwon 2 · lost 0
Claude Sonnet 5won 2 · lost 0
Gemini 3 Prowon 2 · lost 0
Qwen 3.5 Pluswon 2 · lost 0
GPT-6 Solwon 2 · lost 0
O3won 2 · lost 0
Grok 4.5won 2 · lost 0
GLM-5.3 Flashwon 2 · lost 0
Claude Haiku 5.5won 2 · lost 0
Claude Sonnet 4.6won 2 · lost 0
Gemini 3.5 Flashwon 2 · lost 0
Claude Sonnet 4.5won 2 · lost 0
GPT-5.5won 2 · lost 0
Gemini 2.5 Prowon 2 · lost 0
Mimo V2.6 Prowon 2 · lost 0
GLM-5.3won 2 · lost 0
Grok 4.7won 2 · lost 0
GPT-5.4won 2 · lost 0
GPT-6.1 Solwon 2 · lost 0
GPT-5 Miniwon 2 · lost 0
GPT-6 Astrawon 2 · lost 0
GPT-4.1won 2 · lost 0
GPT-5.6 Solwon 2 · lost 0
GPT-5won 2 · lost 0
Muse Wonderwon 1 · lost 1
Muse Spark 1.3won 1 · lost 1
Claude Opus 4.5won 1 · lost 1
GPT-5.2won 1 · lost 1
Claude Opus 4.6won 1 · lost 1
Claude Opus 4.7won 1 · lost 1
Claude Opus 4.8won 1 · lost 1
Claude Opus 5.5won 1 · lost 1
Kimi K3won 1 · lost 1
Claude Sonnet 5.5won 1 · lost 1
Muse Sparkwon 1 · lost 1
Claude Fable 5.1won 1 · lost 1
Muse Spark 1.1won 1 · lost 1
Claude Opus 5won 1 · lost 1
Claude Fable 5won 1 · lost 1
Grok 4.6won 0 · lost 2
Muse Spark 1.2won 0 · lost 2
GPT-5.1won 0 · lost 2
Muse Wonder Fullwon 0 · lost 2
Gemini 4 Argonwon 0 · lost 2

§ 3 · Sources

Where the numbers come from

1 publication, 3 figures. Every one links to the page it was read from.

Vals.ai ↗3 measuresread 2026-10-19
Vals · Legal Research Bench 41.83%Vals · LegalBench 86.23%Vals · Harvey Legal Agent Benchmark 19.17%

Badge

PublicAI Index badge for GLM Legal[![PublicAI Index](https://publicai.io/model-index/badge?model=glm-legal)](https://publicai.io/model-index/m/glm-legal)