GoTry AI

GLM-5.2

Language Zhipu AI Available Released Jun 13, 2026 Partly verified
Model ID
Context
1M
128K max output
Input price
$1.40
per 1M tokens · Z.ai API
Output price
$4.40
per 1M tokens
Epoch Capabilities Index
151.8
#37 of 71 listed
LMArena Text
1,476
#23 of 79 listed

Where to run it

4 offerings · prices as listed
MeterTierPrice
Z.ai API (opens in a new tab) Official Global · USD glm-5.2
InputStandard $1.40 / 1M tokens
OutputStandard $4.40 / 1M tokens
Cache readStandard $0.26 / 1M tokens
Cache writeStandard Free / 1M tokens
SiliconFlow (opens in a new tab) China · CNY zai-org/GLM-5.2
InputStandard ¥8.00 / 1M tokens
OutputStandard ¥28.00 / 1M tokens
Cache readStandard ¥2.00 / 1M tokens
Volcengine Ark (opens in a new tab) Official cn-beijing · CNY glm-5.2
InputStandard ¥8.00 / 1M tokens
OutputStandard ¥28.00 / 1M tokens
Cache readStandard ¥2.00 / 1M tokens
Z.ai API (opens in a new tab) Official China · CNY glm-5.2
InputStandard ¥8.00 / 1M tokens
OutputStandard ¥28.00 / 1M tokens
Cache readStandard ¥2.00 / 1M tokens

Vendor-reported scores

Published by Zhipu AI, under the conditions it states
BenchmarkSettingScore
Humanity's Last Examtext-only subset, no tools40.5%
text-only subset, with tools, 300K max context54.7%
AIME 2026temperature 1.0, 163,840 max generation tokens99.2%
GPQA Diamondtemperature 1.0, 163,840 max generation tokens91.2%
SWE-bench ProOpenHands harness, 400K context62.1%
Terminal-Bench 2.1Terminus-2 harness, 4h timeout, 256K context81%
Claude Code 2.1.167 harness, avg of 5 runs82.7%
MCP-Atlas500-task public subset, think mode, Gemini-3.0-Pro judge76.8%

Cited scores

From third-party leaderboards, not measured by us
  • Epoch Capabilities Index 151.8

    #37 of 71 listed models · CI 149.9–153.6

    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 1,476

    #23 of 79 listed models · max effort · CI 1,471–1,480 · 43,570 votes

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

  • Epoch AI · FrontierMath Tiers 1–3 59.2%

    #29 of 56 listed models · max effort · ±2.96

    Also listed: low effort 54.7% · reasoning off 42.5%

    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 · GPQA Diamond 91.9%

    #16 of 64 listed models · max effort · ±1.61

    Also listed: low effort 87.9% · reasoning off 71.2%

    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 78.7%

    #3 of 23 listed models · max effort · ±1.87

    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 1,519

    #23 of 79 listed models · max effort · CI 1,508–1,530 · 3,128 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 1,512

    #35 of 79 listed models · max effort · CI 1,506–1,519 · 12,052 votes

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