Inference
EN
Z.AI

GLM-5 Thinking

GLM-5 Thinking is a model from Z.AI. 8 benchmarks count toward its index, in 4 categories.

  • Input: text
RankedEnough results for an index.
IndexAll categories, out of 100.53.4±9.2Median 51.0
CoverageIndex weight that has results.65%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.—Median $0.60
Output / 1MUS dollars per 1M output tokens.—Median $2.55
ContextMaximum tokens in one request.—Median 262K
EloLMArena rating and rank.—Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.1 counted56.3—
CodingCode writing and repair.4 counted53.2115 / 209
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.2 counted53.3110 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.1 counted55.6—

Results

8 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
AIMEMath91.7% ±0.823 / 95
Terminal-Bench 2.0 · Vals AIAgentic49.4% ±5.321 / 66
IOI v1Coding22.0% ±7.820 / 61
MMLU ProKnowledge86.0% ±0.350 / 135
LiveCodeBenchCoding81.9% ±1.158 / 142
GPQA Diamond · Vals AIKnowledge83.3% ±1.956 / 135
SWE-benchCoding71.4% ±2.057 / 87
Vibe Code Bench v1.1Coding23.4% ±4.086 / 123
MedQAHealthcare94.3% ±0.218 / 95
LegalBenchLegal84.1% ±0.439 / 149
CorpFin v2Finance62.9% ±0.946 / 131
Finance Agent v1.1Finance53.2% ±2.821 / 51
TaxEval v2Finance70.0% ±0.995 / 143
CaseLaw v2Legal52.5% ±1.744 / 53

Sources

BenchLMCC BY-NC 4.0Vals AINo licence stated

History

5 releases
Index54.4 → 53.4
23 Oct 202612 Nov 2026

Questions

How good is GLM-5 Thinking?
Its index is 53.4 out of 100. That is place 114 of 283 ranked models.
What is GLM-5 Thinking best at?
Knowledge: 53.3 out of 100, place 110 of 268.

Badge

GLM-5 Thinking on Inference360: place 114 of 283, index 53.4
HTML
<a href="https://inference360.ai/models/z-ai-glm-5-thinking"><img src="https://inference360.ai/badges/z-ai-glm-5-thinking.svg" alt="GLM-5 Thinking on Inference360: place 114 of 283, index 53.4" height="20"></a>
Markdown
[![GLM-5 Thinking on Inference360: place 114 of 283, index 53.4](https://inference360.ai/badges/z-ai-glm-5-thinking.svg)](https://inference360.ai/models/z-ai-glm-5-thinking)

Compare with

Grok 4.353.3

More from Z.AI

All models
GLM-5.365.8GLM-5.3-Flash63.1GLM-5.260.6GLM-5.156.0GLM-5-Turbo51.9