Skip to content

Z.ai mit Released Feb 11, 2026 Updated

GLM-5

ToolsGuide Scores, rankings, test results and price.

Model summary

  • Text #66 / 416

    442 / 1,000

    ToolsGuide Score· votes only

  • Coding #85 / 147

    295 / 1,000

    ToolsGuide Score· votes 308, tests 286

  • Price per 1M tokens

    In $1.00· Out $3.20

    $1.00

    Input · median text model $0.43

Summary

GLM-5 is Z.ai's model, released Feb 11, 2026. It's ranked in 2 categories and does best at text: #66 of 416, with a ToolsGuide Score of 442 against a median of 235.

It also ranks #85 of 147 for coding (295).

Its text score uses votes only, because it has published fewer than two of the tests used for that category.

It costs $1.00 per million input tokens and $3.20 per million output tokens, about 2.3× the median text model ($0.43).

It has published results on 5 tests.

Specifications

Creator
Z.ai
Licence
mit
Released
Feb 11, 2026
Context window
200K tokens
Input price
$1.00 / 1M
Output price
$3.20 / 1M
Tests reported
5
Settings ranked
glm-5, GLM-5

Model comparison

Against the ten best text models.

Text score

ToolsGuide Score out of 1,000 · Higher is better

Coding score

ToolsGuide Score out of 1,000 · Higher is better

Input price

USD per 1M input tokens · Lower is better

Leaderboards

Where GLM-5 sits among the top 20 in each category.

Text

#66 of 416 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full text leaderboard →

Coding

#85 of 147 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full coding leaderboard →

By task

Scored from votes on each kind of prompt alone, on the same 1,000-point scale.

Score against price

Text · the 10 priced models ranked closest · up and to the left is better value

Against its nearest rivals

Text prompts by kind · ToolsGuide Score from votes · hover for values

Text

glm-5 · hover a bar for its rank

Coding

GLM-5 · hover a bar for its rank

Test results

Every test GLM-5 has a published result on, out of 100%, with its rank among the models that took it.

  • SWE-Bench Verified

    #25 / 120

    Fixing real bugs in real GitHub projects, checked by the projects' own tests.

    77.8%

    Self-reported

  • BrowseComp

    #28 / 68

    Finding hard-to-locate facts by browsing the web.

    75.9%

    Self-reported · In the agents score

  • Terminal-Bench 2.0

    #29 / 54

    Getting real work done in a command-line terminal.

    56.2%

    Self-reported

  • MCP Atlas

    #25 / 38

    MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.

    67.8%

    Self-reported

  • t2-bench

    #3 / 23

    t2-bench is a benchmark for evaluating agentic tool use capabilities, measuring how well models can select, sequence, and utilize tools to solve complex tasks. It tests autonomous planning and execution in multi-step scenarios.

    89.7%

    Self-reported