Models / GLM-5.2

Z.ai

GLM-5.2

GLM-5.2 is best for writing, and reasoning and knowledge; a strong pick at a modest price. The cheapest model of similar intelligence is MiMo-V2.6-Flash, at $0.18 per million tokens against $2.15.

Superseded. GLM-5.3 is Z.ai's newer model in this line, at $2.15 blended: see GLM-5.3 or compare the two.

Results 16 Nov 2026 · 40 results · 6 sources

Test GLM-5.2 on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$1.40 in · $4.40 out
Z.ai's list price, 10 Nov 2026 · compare prices$0.26 cached input
Speed
Not measured
Intelligence Index
33.7
Artificial Analysis, at max reasoning; 22.4–33.7 across 2 settings
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Z.ai, based in China
Weights published
Released
16 Jun 2026
1,048,576 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location, plus models with published weights. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 44th of 185Claude Opus 5.5 – $2.15 blended, 71st percentilecheapest: Mistral Nemo –
Models priced $1–3 per million tokens 7th of 34Muse Spark 1.3 – sets this group –
Models with similar intelligence sets this group – $2.15 blended, 57th percentilecheapest: DeepSeek-V4-Flash (0731) –
Models from developers based in China 14th of 75MiMo-V2.6-Pro – $2.15 blended, 92nd percentilecheapest: Qwen3.5-9B –
Open-weights models 15th of 104MiMo-V2.6-Pro – $2.15 blended, 95th percentilecheapest: Mistral Nemo –

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced $1–3 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 47th of 159 available · 9th of 31 at its price
BenchmarkGLM-5.2Rank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 1.0% 56th of 107 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 77.9% 28th of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 34.6% 25th of 104 Grok 4.6 50.7%
Vending-Bench 2Vending-Bench 2: money after a year · reported $8,314 7th of 53 GPT-6 Astra $15,515
  • tau2-bench: pending. Its latest results are dated 26 May 2026, before this model was released.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • OpenHands Index: has not measured this model.
  • Microsoft STATE-Bench: pending. Its latest results are dated 29 May 2026, before this model was released.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects Not measured
  • APEX-Agents: has not measured this model.
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 50th of 187 available · 9th of 35 at its price
BenchmarkGLM-5.2Rank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 33.7 44th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 41.1% 40th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 89.5% 46th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 27th of 169 available · 5th of 28 at its price
BenchmarkGLM-5.2Rank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,476 25th of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 67.0 18th of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 64th of 139 available · 12th of 26 at its price
BenchmarkGLM-5.2Rank among availableBest available
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,463 32nd of 109 Gemini 4 Argon 1,511
SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported 34.2% 47th of 68 GPT-6 Astra 75.6%
  • Vectara Hallucination Leaderboard: has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against GLM-5.2 at $2.15 blended, Intelligence Index 33.7. "Similar intelligence" means within 4 points or better.

Where to run it

28 hosts on OpenRouter at the standard service tier, with a median of $2.14 blended per million tokens; quantisation where the host states it: FP4, FP8, NVFP4. Cheapest first.

HostQuantisationInputOutputBlended
DeepInfraFP4$0.56$1.80$0.87
StreamLakeFP8$0.61$1.93$0.94
AmbientFP8$0.60$2.00$0.95
NovitaFP8$0.65$2.04$1.00
CoreWeaveFP4$0.62$2.42$1.07
DigitalOceannot stated$0.70$2.20$1.07
SiliconFlowFP8$0.70$2.20$1.07
MorphFP8$1.05$2.15$1.33

Other service tiers, not counted above: BaseTen fast $2.10 in, $6.60 out; BaseTen fast $2.10 in, $6.60 out; Alibaba fast $2.31 in, $7.26 out; Baidu fast $2.25 in, $7.88 out; DeepInfra flex $0.45 in, $1.44 out. Flex and batch are cheaper but slower or queued; priority and fast cost more.

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026; the 20 dearer hosts are left out.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

GLM-5.2Muse Spark 1.3
most intelligent at $1–3 per million tokens
DeepSeek-V4-Flash (0731)
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
MiMo-V2.6-Pro
most intelligent from China
Price per million tokens $2.15 $2.00$0.20$8.00$0.54
Tokens a second – 254–9643
Intelligence Index 33.7 48.134.357.646.3
Spring Prompt overall – 59–82–
Rank among available models, by use case
Product listings – 17th–13th–
Decks from an analysis – 25th–7th–
User surveys – ––4th–
Marketing planning – 25th–9th–
Agents and tool use 47th of 159 13th43rd3rd23rd
Professional work – 8th–3rd–
Reasoning and knowledge 50th of 187 11th47th1st13th
Writing 27th of 169 7th–5th23rd
Sticking to the facts 64th of 139 11th105th3rd10th
Speed under pressure – 33rd–––

Shaded figures are better than GLM-5.2's. A dash means no result.

Where it has been measured

7th most intelligent of the 34 models priced $1–3 per million tokens. Among models available today, in the top quarter (by percentile) for writing, and reasoning and knowledge.

Artificial Analysis lists it but has not published a speed for it yet

Every result

40 published results from 6 sources, each in the source's own units, with the configuration that produced it.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 11 results
MeasureValueRankConfigurationDated
Arena Agent: confirmed task successIPS effect estimate, higher is better 0.05
0.03–0.06
20 of 50 GLM-5.2 (max reasoning, arena agent) 2 Oct 2026
Arena Agent: praise over complaintIPS effect estimate, higher is better 0.10
0.07–0.13
13 of 50 GLM-5.2 (max reasoning, arena agent) 2 Oct 2026
Arena Agent: steerabilityIPS effect estimate, higher is better 0.01
0.01–0.02
23 of 50 GLM-5.2 (max reasoning, arena agent) 2 Oct 2026
Arena Agent: tool groundingIPS effect estimate, higher is better 0.00
0.00–0.00
10 of 50 GLM-5.2 (max reasoning, arena agent) 2 Oct 2026
Arena Text factuality: overallArena rating, higher is better 1,463
1,460–1,467
43 of 182 GLM-5.2 (max reasoning) 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,465
1,458–1,473
48 of 406 GLM-5.2 (max reasoning) 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,454
1,447–1,462
32 of 411 GLM-5.2 (max reasoning) 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,502
1,493–1,511
41 of 363 GLM-5.2 (max reasoning) 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,470
1,464–1,475
37 of 413 GLM-5.2 (max reasoning) 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,476
1,471–1,480
32 of 413 GLM-5.2 (max reasoning) 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,459
1,453–1,466
38 of 412 GLM-5.2 (max reasoning) 2 Oct 2026

Not shown: Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.

Artificial Analysis · reported by Artificial Analysis · 19 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 68.8 56 of 187 GLM-5.2 (max reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 46.5 107 of 187 GLM-5.2 (no reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 33.7 97 of 413 GLM-5.2 (max reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 22.4 185 of 413 GLM-5.2 (no reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 89.5% 75 of 360 GLM-5.2 (max reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 68.6% 253 of 360 GLM-5.2 (no reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 41.1% 80 of 419 GLM-5.2 (max reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 9.8% 284 of 419 GLM-5.2 (no reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 73.3% 37 of 288 GLM-5.2 (max reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 78.3% 109 of 407 GLM-5.2 (max reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 42.3% 310 of 407 GLM-5.2 (no reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 51.2% 101 of 205 GLM-5.2 (max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 77.9% 55 of 188 GLM-5.2 (max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 51.7% 104 of 188 GLM-5.2 (no reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 1.0% 134 of 204 GLM-5.2 (max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 50.8% 22 of 282 GLM-5.2 (max reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 34.6% 48 of 175 GLM-5.2 (max reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 16.7% 95 of 175 GLM-5.2 (no reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 99.1% 1 of 286 GLM-5.2 (max reasoning) 20 Oct 2026

Not shown: Not your codebase or tools.

SimpleQA Verified (Epoch AI) · reported by SimpleQA Verified (Epoch AI) · 1 result
MeasureValueRankConfigurationDated
SimpleQA Verified: correct answers% of questions, higher is better 34.2% 53 of 85 GLM-5.2 (max reasoning) 27 Aug 2026

Not shown: Not answers grounded in your documents; tests what the model remembers.

tau2-bench · reported by tau2-bench · 2 results
MeasureValueRankConfigurationDated
tau2 v1.0.1, banking knowledge, alltools retrieval: consistency (pass^4)% of tasks, higher is better 13.4% 13 of 21 GLM-5.2 (xhigh reasoning, tau2) 24 Jul 2026
tau2 v1.0.1, banking knowledge, alltools retrieval: task success (pass^1)% of tasks, higher is better 37.1% 11 of 21 GLM-5.2 (xhigh reasoning, tau2) 24 Jul 2026

Not shown: Not your policies or customers: the tasks and policies are tau2's own, and the customer is simulated by gpt-5.2.

UGI Leaderboard · reported by UGI Leaderboard · 6 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 12.0% 106 of 379 GLM-5.2 (no reasoning) 21 Jun 2026
UGI: requested-length error% off the requested word count, lower is better 18.0% 158 of 379 GLM-5.2 (thinking reasoning) 21 Jun 2026
UGI: style adherencescore from 0 to 1, higher is better 0.37 85 of 379 GLM-5.2 (no reasoning) 21 Jun 2026
UGI: style adherencescore from 0 to 1, higher is better 0.35 199 of 379 GLM-5.2 (thinking reasoning) 21 Jun 2026
UGI: writing scorescore out of 100, higher is better 61.2 95 of 379 GLM-5.2 (no reasoning) 21 Jun 2026
UGI: writing scorescore out of 100, higher is better 67.0 48 of 379 GLM-5.2 (thinking reasoning) 21 Jun 2026

Not shown: Not other format limits such as character counts or bullet counts.

Vending-Bench 2 · reported by Vending-Bench 2 · 1 result
MeasureValueRankConfigurationDated
Vending-Bench 2: money after a yearUS dollars, higher is better $8,314 7 of 63 GLM-5.2 1 Oct 2026

Not shown: Not a real business; one simulated market with set rules.

Will GLM-5.2 work for your product?

Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.

New here? Your email starts a free trial. No credit card needed.