GoTry AI

GLM-5

Language Zhipu AI Available Released Feb 11, 2026 Partly verified
Model ID
Context
200K
128K max output
Input price
$1.00
per 1M tokens · Z.ai API
Output price
$3.20
per 1M tokens
Epoch Capabilities Index
145.8
#56 of 71 listed
LMArena Text
1,457
#36 of 79 listed

Where to run it

2 offerings · prices as listed
MeterTierPrice
Z.ai API (opens in a new tab) Official Global · USD glm-5
InputStandard $1.00 / 1M tokens
OutputStandard $3.20 / 1M tokens
Cache readStandard $0.20 / 1M tokens
Cache writeStandard Free / 1M tokens
Z.ai API (opens in a new tab) Official China · CNY glm-5
InputStandard ¥4.00 / 1M tokens
Prompts over 32K tokens ¥6.00 / 1M tokens
OutputStandard ¥18.00 / 1M tokens
Prompts over 32K tokens ¥22.00 / 1M tokens
Cache readStandard ¥1.00 / 1M tokens
Prompts over 32K tokens ¥1.50 / 1M tokens

Vendor-reported scores

Published by Zhipu AI, under the conditions it states
BenchmarkSettingScore
Humanity's Last Examtext-only subset, no tools, 131,072 max generation tokens30.5%
text-only subset, with tools, 202,752 max context50.4%
GPQA Diamondtemperature 1.0, 131,072 max generation tokens86%
SWE-bench VerifiedOpenHands harness, 200K context77.8%
Terminal-Bench 2.0Terminus 2 harness, 2h timeout, 128K context56.2%
Claude Code 2.1.14 harness, think mode, avg of 5 runs56.2%
BrowseCompwithout context management (last 5 turns kept)62%
with discard-all context management75.9%
τ²-benchwith vendor prompt adjustments (Retail, Telecom) and Airline domain fixes89.7%
MCP-Atlas500-task public subset, think mode, Gemini 3 Pro judge67.8%

Cited scores

From third-party leaderboards, not measured by us
  • Epoch Capabilities Index 145.8

    #56 of 71 listed models · CI 143.7–147.7

    Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made

  • LMArena Text 1,457

    #36 of 79 listed models · CI 1,453–1,462 · 29,152 votes

    LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made

  • Epoch AI · GPQA Diamond 87.8%

    #37 of 64 listed models · ±2.34

    Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made

  • Epoch AI · SWE-bench Verified 72.1%

    #18 of 23 listed models · ±2.09

    Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made

  • LMArena Text · Chinese 1,516

    #26 of 79 listed models · CI 1,503–1,530 · 2,002 votes

    LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made

  • LMArena Text · Coding 1,498

    #43 of 79 listed models · CI 1,490–1,505 · 7,622 votes

    LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made