Z.ai, released Jun 13, 2026

GLM-5.2price, context, benchmarks and release details

Provisional: not enough results to rank yet Open weights 100% confidence 100 percent, Full confidence, 5 of 7 expected sources in
65.7
SI Score
#34 of 142 ranked models
Input, per 1M tokens
$1.40Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded Retrieved Oct 9, 2026 · factual citation
Open source ↗
Output, per 1M tokens
$4.40Z.ai API pricingOfficial Z.ai global Standard uncached token rate; coding-plan subscriptions, cache and Batch excluded Retrieved Oct 9, 2026 · factual citation
Open source ↗
Context window
1Mmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Max output
131Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
Jun 13, 2026models.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗

How the score breaks down

Coding (weight 40 percent) 66.2
Math (weight 15 percent) 70.4
Preference (weight 15 percent) 79.4
Reasoning (weight 30 percent) 68.3

Weights: reasoning 30%, math 15%, coding 40%, preference 15%. Results use fixed 0–100 scales before averaging, and thin evidence is pulled toward 50. Method si-v3-retained-evidence-2, computed Oct 9, 2026, 06:15 UTC.

Around it on the leaderboard

  1. 32 Kimi K2 Thinking Turbo 66.1
  2. 33 GPT-5.2 65.9
  3. 34 GLM-5.2 65.7
  4. 35 Gemini 3.6 Flash 65.5
  5. 36 Grok 4.7 65.5

Full leaderboard

Benchmark results

30 benchmarks, 38 results

Each row shows the best published result. Where a model was tested at several settings, such as reasoning effort, open the row to see each one. Hover or tap a value for its source.

ARC-AGI-1 (public eval)reasoning 80.4%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] glm-5.2Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 80.4
ARC-AGI-1 (semi-private)reasoning 77%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] glm-5.2Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 77.0
ARC-AGI-2 (public eval)reasoning 20.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] glm-5.2Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 20.8
ARC-AGI-2 (semi-private)reasoning 22.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] glm-5.2Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 22.8
GPQA Diamondreasoning 91.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 24, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 91.9 4 settings
  • no reasoning 71.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 10, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • low effort 87.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 10, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • max effort 91.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 24, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • Setting 4 91.2%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] Published Jun 16, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
    Open source ↗
About GPQA Diamond
Humanity's Last Exam (text-only subset, with tools)reasoning 54.7%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] with tools; text-only subsetPublished Jun 16, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 54.7
Humanity's Last Exam (text-only subset)reasoning 40.5%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] text-only subsetPublished Jun 16, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 40.5
LiveBench Reasoning: connectionsreasoning 94%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 94.0
LiveBench Reasoning: consecutive eventsreasoning 79.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 79.3
LiveBench Reasoning: logic with navigationreasoning 80%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 80.0
LiveBench Reasoning: spatialreasoning 94%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 94.0
LiveBench Reasoning: theory of mindreasoning 75%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 75.0
LiveBench Reasoning: zebra puzzlesreasoning 65.5%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 65.5
FrontierMath Tier 4 (v2)math 29.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 19, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 29.3
FrontierMath Tiers 1–3 (v2)math 59.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 19, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 59.2 3 settings
  • no reasoning 42.5%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 29, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • low effort 54.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 29, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • max effort 59.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 19, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About FrontierMath Tiers 1–3 (v2)
LiveBench Math: AMPS Hardmath 98%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 98.0
LiveBench Math: competition mathmath 96.1%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 96.1
LiveBench Math: integralsmath 76%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 76.0
LiveBench Math: olympiadmath 89.0%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 89.0
LiveBench Math: simplifymath 55.7%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 55.7
OTIS Mock AIME 2024–2025math 86.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 25, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 86.4 3 settings
  • no reasoning 28.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 10, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • low effort 75.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 10, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • max effort 86.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 25, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About OTIS Mock AIME 2024–2025
LiveBench Coding: code completioncoding 80.4%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 80.4
LiveBench Coding: code generationcoding 78.9%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 78.9
LiveBench Coding: JavaScriptcoding 63.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 63.6
LiveBench Coding: Pythoncoding 55%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 55.0
LiveBench Coding: TypeScriptcoding 36.7%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 36.7
SWE-bench Procoding 62.1%Official model cards via models.devLab-reported; metric resolve rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] Published Jun 16, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 62.1
SWE-bench Verifiedcoding 78.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 25, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 78.7
Terminal-Bench 2.1coding 82.7%Official model cards via models.devLab-reported; metric success rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] Claude Code; 2.1Published Jun 16, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 82.7 2 settings
  • Setting 1 82.7%Official model cards via models.devLab-reported; metric success rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] Claude Code; 2.1Published Jun 16, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
    Open source ↗
  • Setting 2 81%Official model cards via models.devLab-reported; metric success rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] Terminus 2; 2.1Published Jun 16, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
    Open source ↗
About Terminal-Bench 2.1
LMArena Textpreference 1469.8 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 8, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 79.4

Normalization uses a fixed 0–100 scale for each unit, independent of other models. Compare evaluation conditions before reading a small gap as decisive. “Lab-reported” marks the provider's own published figure.

Details and sources

Open weights
YesHugging Face HubPublic Hub repo with weight files; gating/repo upload date is not release date Retrieved Oct 9, 2026 · factual metadata; model-specific licenses
Open source ↗
License
mitHugging Face HubPublished source fact Retrieved Oct 9, 2026 · factual metadata; model-specific licenses
Open source ↗
Input modalities
textmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
First seen by SuperIndex
Oct 8, 2026
Coverage
81% of expected source weight

Reported (5)

  • ARC PrizeOct 8, 2026
  • Epoch AI BenchmarkingOct 8, 2026
  • Official model cards via models.devOct 8, 2026
  • LiveBenchOct 8, 2026
  • LMArena / ArenaOct 8, 2026

Awaiting (2)

  • Humanity’s Last Exam13% of weight
  • Terminal-Bench6% of weight

Confidence rises as pending sources publish. Some sources never cover some models, so confidence reaches 100% at 80% of expected weight.

What changed

All releases · RSS feed

Alerts on this device

What to be alerted about
RSS feed