Back

Z.AI

GLM-5.1

ReasoningOpen weightsModels.dev
Intelligence
26.1
Rank 163 of 744 measured models
Coding
55.8
Rank 105 of 298 measured models
Output speed
65.4 t/s
Rank 262 of 403 measured models
Price/1M
$1.98
Rank 465 of 659 measured models
Context window
200K
Rank 618 of 1199 measured models
Cost per task
$1.02
Rank 131 of 193 measured models

GLM-5.1 (Reasoning) scores 26.1 on the Artificial Analysis Intelligence Index, ranking 163rd of 744 measured models. The closest models on this index are Gemini 3 Flash Preview (batch) (26.3), GPT-5.5 Instant (June 2026) (26.0), and MiMo-V2.5-Pro (26.0). At $1.98 per million tokens (3:1 input/output blended price), it is cheaper than GPT-5.5 Instant (June 2026) ($11.25), more expensive than MiMo-V2.5-Pro ($0.544). With an output speed of 65.4 t/s, it is faster than MiMo-V2.5-Pro (38.8 t/s), slower than GPT-5.5 Instant (June 2026) (151 t/s).

Artificial Analysis Indices
Reasoning
Intelligence26.1
Rank 163 of 744 measured models
Coding55.8
Rank 105 of 298 measured models
Agentic23.9
Rank 86 of 189 measured models
Reasoning levels
Each point is a reasoning level of this model: more reasoning often raises the score but costs more. Select a point to open that level.
Intelligence Indexmost efficient ↗Price / 1M tokens
Capability indexes
Performance in specific industries, measured by Artificial Analysis
Finance & Accounting26.3
Rank 131 of 218 measured models
Strategy & Ops23.3
Rank 133 of 218 measured models
Legal28.8
Rank 125 of 218 measured models
Engineering30.2
Rank 113 of 217 measured models
Economics37.6
Rank 116 of 225 measured models
Standard Benchmarks
GPQA Diamond86.8%
Rank 112 of 619 measured models
HLE30.1%
Rank 150 of 664 measured models
SciCode44.8%
Rank 146 of 231 measured models
IFBench76.3%
Rank 23 of 450 measured models
AA-LCR73.7%
Rank 176 of 575 measured models
TerminalBench Hard43.2%
Rank 41 of 432 measured models
Terminal-Bench 2.161.8%
Rank 96 of 244 measured models
Terminal-Bench v42.0%
Rank 114 of 218 measured models
Additional benchmarks21
Design Arena · 3d62.6%
Design Arena · Agenticgamedev49.8%
Design Arena · Agentichtmlslides52.0%
Design Arena · Agenticslides Html51.8%
Design Arena · Agenticslides Python Pptx53.3%
Design Arena · Agenticslides54.4%
Design Arena · Androidnative52.0%
Design Arena · Asciiart44.9%
Design Arena · Codecategories53.1%
Design Arena · Dataviz67.0%
Design Arena · Fullstack53.2%
Design Arena · Gamedev55.2%
Design Arena · Godotgamedev37.8%
Design Arena · Htmlslides48.8%
Design Arena · Mobileapps50.6%
Design Arena · Pptxslides53.5%
Design Arena · Python Pptxslides54.2%
Design Arena · Svg55.5%
Design Arena · Uicomponent54.9%
Design Arena · Webapps50.7%
Design Arena · Website55.1%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy