Models / GLM-5

Z.ai

GLM-5

GLM-5 is strongest at writing; worth a look for simple, high-volume work where cost matters most. The cheapest model of similar intelligence is DeepSeek-V4-Flash (0423), at $0.15 per million tokens against $1.55.

Superseded.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 · 44 results · 7 sources

Test GLM-5 on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$1.00 in · $3.20 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
Not measured
Intelligence Index
27.9
Artificial Analysis; 21.8–27.9 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
12 Feb 2026
204,800 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 59th of 185Claude Opus 5.5 – $1.55 blended, 63rd percentilecheapest: Mistral Nemo –
Models priced $1–3 per million tokens 12th of 34Muse Spark 1.3 – sets this group –
Models with similar intelligence sets this group – $1.55 blended, 41st percentilecheapest: DeepSeek-V4-Flash (0423) –
Models from developers based in China 19th of 75MiMo-V2.6-Pro – $1.55 blended, 83rd percentilecheapest: Qwen3.5-9B –
Open-weights models 20th of 104MiMo-V2.6-Pro – $1.55 blended, 87th 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 102nd of 159 available · 26th of 31 at its price
BenchmarkGLM-5Rank among availableBest available
tau2-benchtau2 v1.0.1, retail: task success (pass^1) · reported 73.7% 5th of 6 Qwen3.5-397B-A17B 84.4%
tau2-benchtau2 v1.0.1, airline: task success (pass^1) · reported 82.5% 3rd of 6 Claude Opus 4.5 84.0%
tau2-benchtau2 v1.0.1, telecom: task success (pass^1) · reported 86.8% 5th of 6 Qwen3.5-397B-A17B 97.8%
OpenHands IndexOpenHands Index: average · reported 49.4% 17th of 31 Claude Fable 5 81.0%
Vending-Bench 2Vending-Bench 2: money after a year · reported $4,432 29th of 53 GPT-6 Astra $15,515
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • Microsoft STATE-Bench: has not measured this model.
  • Artificial Analysis: has not measured this model.
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 83rd of 187 available · 25th of 35 at its price
BenchmarkGLM-5Rank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 27.9 59th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 29.3% 78th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 82.0% 86th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 51st of 169 available · 13th of 28 at its price
BenchmarkGLM-5Rank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,458 41st of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 55.0 44th of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 66th of 139 available · 13th of 26 at its price
BenchmarkGLM-5Rank among availableBest available
Vectara Hallucination LeaderboardVectara: hallucination rate · reported 10.1% 41st of 71 GPT-5.4 nano 3.1%
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,452 47th of 109 Gemini 4 Argon 1,511
  • SimpleQA Verified (Epoch AI): 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 at $1.55 blended, Intelligence Index 27.9. "Similar intelligence" means within 4 points or better.

Where to run it

9 hosts on OpenRouter at the standard service tier, with a median of $1.55 blended per million tokens; quantisation where the host states it: FP8. Cheapest first.

HostQuantisationInputOutputBlended
GMICloudFP8$0.60$1.92$0.93
StreamLakeFP8$0.60$1.92$0.93
BaiduFP8$0.70$2.24$1.08
SiliconFlowFP8$0.95$2.55$1.35
Amazon Bedrocknot stated$1.00$3.20$1.55
NovitaFP8$1.00$3.20$1.55
VeniceFP8$1.00$3.20$1.55
Z.AIFP8$1.00$3.20$1.55

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026; the 1 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-5Muse Spark 1.3
most intelligent at $1–3 per million tokens
DeepSeek-V4-Flash (0423)
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
MiMo-V2.6-Pro
most intelligent from China
Price per million tokens $1.55 $2.00$0.15$8.00$0.54
Tokens a second – 254–9643
Intelligence Index 27.9 48.124.457.646.3
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 102nd of 159 13th59th3rd23rd
Professional work – 8th–3rd–
Reasoning and knowledge 83rd of 187 11th69th1st13th
Writing 51st of 169 7th63rd5th23rd
Sticking to the facts 66th of 139 11th81st3rd10th
Speed under pressure – 33rd–––

Shaded figures are better than GLM-5's. A dash means no result.

Where it has been measured

12th most intelligent of the 34 models priced $1–3 per million tokens. Among models available today, mid-field on every use case measured so far.

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

Every result

44 published results from 7 sources, each in the source's own units, with the configuration that produced it.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 7 results
MeasureValueRankConfigurationDated
Arena Text factuality: overallArena rating, higher is better 1,452
1,448–1,456
64 of 182 GLM-5 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,451
1,443–1,459
75 of 406 GLM-5 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,449
1,440–1,458
40 of 411 GLM-5 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,482
1,470–1,493
70 of 363 GLM-5 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,446
1,440–1,453
71 of 413 GLM-5 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,458
1,453–1,462
63 of 413 GLM-5 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,449
1,441–1,456
55 of 412 GLM-5 2 Oct 2026

Not shown: Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.

Artificial Analysis · reported by Artificial Analysis · 14 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 27.9 131 of 413 GLM-5 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 21.8 191 of 413 GLM-5 (no reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 82.0% 159 of 360 GLM-5 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 66.6% 269 of 360 GLM-5 (no reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 29.3% 153 of 419 GLM-5 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 7.6% 303 of 419 GLM-5 (no reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 72.3% 45 of 288 GLM-5 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 55.2% 119 of 288 GLM-5 (no reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 75.7% 149 of 407 GLM-5 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 43.7% 303 of 407 GLM-5 (no reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 43.2% 40 of 282 GLM-5 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 39.4% 55 of 282 GLM-5 (no reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 98.2% 6 of 286 GLM-5 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 97.4% 10 of 286 GLM-5 (no reasoning) 20 Oct 2026

Not shown: Not business work, and a blend: read the parts for any one task.

OpenHands Index · reported by OpenHands Index · 6 results
MeasureValueRankConfigurationDated
OpenHands Index: average% resolved, higher is better 49.4% 17 of 34 GLM-5 (openhands) 30 Jun 2026
OpenHands Index: front end (SWE-Bench Multimodal)% resolved, higher is better 35.3% 17 of 34 GLM-5 (openhands) 30 Jun 2026
OpenHands Index: greenfield (Commit0)% resolved, higher is better 31.2% 13 of 34 GLM-5 (openhands) 30 Jun 2026
OpenHands Index: information gathering (GAIA)% resolved, higher is better 60.0% 18 of 34 GLM-5 (openhands) 30 Jun 2026
OpenHands Index: issue resolution (SWE-Bench)% resolved, higher is better 73.4% 20 of 34 GLM-5 (openhands) 30 Jun 2026
OpenHands Index: testing (SWT-Bench)% resolved, higher is better 47.3% 27 of 34 GLM-5 (openhands) 30 Jun 2026

Not shown: Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.

tau2-bench · reported by tau2-bench · 8 results
MeasureValueRankConfigurationDated
tau2 v1.0.1, airline: consistency (pass^4)% of tasks, higher is better 70.0% 2 of 8 GLM-5 (thinking reasoning, tau2) 27 Feb 2026
tau2 v1.0.1, airline: task success (pass^1)% of tasks, higher is better 82.5% 3 of 8 GLM-5 (thinking reasoning, tau2) 27 Feb 2026
tau2 v1.0.1, banking knowledge, text-emb-3-large retrieval: consistency (pass^4)% of tasks, higher is better 3.1% 2 of 2 GLM-5 (thinking reasoning, tau2) 27 Feb 2026
tau2 v1.0.1, banking knowledge, text-emb-3-large retrieval: task success (pass^1)% of tasks, higher is better 9.8% 1 of 2 GLM-5 (thinking reasoning, tau2) 27 Feb 2026
tau2 v1.0.1, retail: consistency (pass^4)% of tasks, higher is better 43.9% 7 of 8 GLM-5 (thinking reasoning, tau2) 27 Feb 2026
tau2 v1.0.1, retail: task success (pass^1)% of tasks, higher is better 73.7% 7 of 8 GLM-5 (thinking reasoning, tau2) 27 Feb 2026
tau2 v1.0.1, telecom: consistency (pass^4)% of tasks, higher is better 62.3% 7 of 8 GLM-5 (thinking reasoning, tau2) 27 Feb 2026
tau2 v1.0.1, telecom: task success (pass^1)% of tasks, higher is better 86.8% 6 of 8 GLM-5 (thinking reasoning, tau2) 27 Feb 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 36.0% 290 of 379 GLM-5 (no reasoning) 11 Feb 2026
UGI: requested-length error% off the requested word count, lower is better 34.0% 278 of 379 GLM-5 (thinking reasoning) 11 Feb 2026
UGI: style adherencescore from 0 to 1, higher is better 0.40 23 of 379 GLM-5 (no reasoning) 11 Feb 2026
UGI: style adherencescore from 0 to 1, higher is better 0.38 61 of 379 GLM-5 (thinking reasoning) 11 Feb 2026
UGI: writing scorescore out of 100, higher is better 49.2 170 of 379 GLM-5 (no reasoning) 11 Feb 2026
UGI: writing scorescore out of 100, higher is better 55.0 132 of 379 GLM-5 (thinking reasoning) 11 Feb 2026

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

Vectara Hallucination Leaderboard · reported by Vectara Hallucination Leaderboard · 2 results
MeasureValueRankConfigurationDated
Vectara: answer rate% of documents, higher is better 99.7% 44 of 108 GLM-5 22 Sep 2026
Vectara: hallucination rate% of summaries, lower is better 10.1% 59 of 108 GLM-5 22 Sep 2026

Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.

Vending-Bench 2 · reported by Vending-Bench 2 · 1 result
MeasureValueRankConfigurationDated
Vending-Bench 2: money after a yearUS dollars, higher is better $4,432 33 of 63 GLM-5 1 Oct 2026

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

Will GLM-5 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.