Models / GLM-4.7

Z.ai

GLM-4.7

GLM-4.7 is strongest at reasoning and knowledge; 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 $1.00.

Superseded.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 · 7 sources

Test GLM-4.7 on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$0.60 in · $2.20 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
Not measured
Intelligence Index
22.2
Artificial Analysis; 17.4–22.2 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
22 Dec 2025
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 88th of 185Claude Opus 5.5 – $1.00 blended, 56th percentilecheapest: Mistral Nemo –
Models priced $1–3 per million tokens 25th of 34Muse Spark 1.3 – sets this group –
Models with similar intelligence sets this group – $1.00 blended, 50th percentilecheapest: DeepSeek-V4-Flash (0423) –
Models from developers based in China 35th of 75MiMo-V2.6-Pro – $1.00 blended, 69th percentilecheapest: Qwen3.5-9B –
Open-weights models 35th of 104MiMo-V2.6-Pro – $1.00 blended, 76th 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 108th of 159 available · 27th of 31 at its price
BenchmarkGLM-4.7Rank among availableBest available
OpenHands IndexOpenHands Index: average · reported 42.3% 25th of 31 Claude Fable 5 81.0%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 45.3% 64th of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 12.2% 65th of 104 Grok 4.6 50.7%
Vending-Bench 2Vending-Bench 2: money after a year · reported $2,377 37th of 53 GPT-6 Astra $15,515
  • tau2-bench: has not measured this model.
  • 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.
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 87th of 187 available · 26th of 35 at its price
BenchmarkGLM-4.7Rank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 22.2 88th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 27.4% 87th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 85.9% 65th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 73rd of 169 available · 20th of 28 at its price
BenchmarkGLM-4.7Rank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,441 61st of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 47.4 61st of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 97th of 139 available · 22nd of 26 at its price
BenchmarkGLM-4.7Rank among availableBest available
Vectara Hallucination LeaderboardVectara: hallucination rate · reported 11.7% 52nd of 71 GPT-5.4 nano 3.1%
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,444 60th of 109 Gemini 4 Argon 1,511
SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported 32.2% 52nd of 68 GPT-6 Astra 75.6%
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against GLM-4.7 at $1.00 blended, Intelligence Index 22.2. "Similar intelligence" means within 4 points or better.

Where to run it

5 hosts on OpenRouter at the standard service tier, with a median of $1.00 blended per million tokens; quantisation where the host states it: FP4, FP8. Cheapest first.

HostQuantisationInputOutputBlended
DeepInfraFP4$0.40$1.75$0.74
VeniceFP4$0.40$1.93$0.78
NovitaFP8$0.60$2.20$1.00
Z.AIFP4$0.60$2.20$1.00
Mancer 2FP4$0.70$2.50$1.15

Other service tiers, not counted above: DeepInfra flex $0.32 in, $1.40 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.

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-4.7Muse 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 $1.00 $2.00$0.15$8.00$0.54
Tokens a second – 254–9643
Intelligence Index 22.2 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 108th of 159 13th59th3rd23rd
Professional work – 8th–3rd–
Reasoning and knowledge 87th of 187 11th69th1st13th
Writing 73rd of 169 7th63rd5th23rd
Sticking to the facts 97th of 139 11th81st3rd10th
Speed under pressure – 33rd–––

Shaded figures are better than GLM-4.7's. A dash means no result.

Where it has been measured

25th 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

40 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 1,444
1,438–1,450
84 of 182 GLM-4.7 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,442
1,430–1,455
95 of 406 GLM-4.7 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,405
1,391–1,418
103 of 411 GLM-4.7 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,449
1,428–1,469
116 of 363 GLM-4.7 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,425
1,415–1,436
103 of 413 GLM-4.7 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,441
1,435–1,448
93 of 413 GLM-4.7 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,416
1,405–1,427
98 of 412 GLM-4.7 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 · 17 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 45.3 110 of 187 GLM-4.7 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 22.2 187 of 413 GLM-4.7 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 17.4 233 of 413 GLM-4.7 (no reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 85.9% 115 of 360 GLM-4.7 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 66.4% 271 of 360 GLM-4.7 (no reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 27.4% 170 of 419 GLM-4.7 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 6.4% 323 of 419 GLM-4.7 (no reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 67.9% 75 of 288 GLM-4.7 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 54.6% 122 of 288 GLM-4.7 (no reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 71.0% 191 of 407 GLM-4.7 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 40.7% 317 of 407 GLM-4.7 (no reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 45.3% 115 of 188 GLM-4.7 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 31.8% 97 of 282 GLM-4.7 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 30.3% 107 of 282 GLM-4.7 (no reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 12.2% 115 of 175 GLM-4.7 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 95.9% 14 of 286 GLM-4.7 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 94.2% 30 of 286 GLM-4.7 (no reasoning) 20 Oct 2026

Not shown: Not your codebase or tools.

OpenHands Index · reported by OpenHands Index · 6 results
MeasureValueRankConfigurationDated
OpenHands Index: average% resolved, higher is better 42.3% 26 of 34 GLM-4.7 (openhands) 30 Jun 2026
OpenHands Index: front end (SWE-Bench Multimodal)% resolved, higher is better 22.1% 30 of 34 GLM-4.7 (openhands) 30 Jun 2026
OpenHands Index: greenfield (Commit0)% resolved, higher is better 12.5% 25 of 34 GLM-4.7 (openhands) 30 Jun 2026
OpenHands Index: information gathering (GAIA)% resolved, higher is better 53.9% 20 of 34 GLM-4.7 (openhands) 30 Jun 2026
OpenHands Index: issue resolution (SWE-Bench)% resolved, higher is better 73.4% 20 of 34 GLM-4.7 (openhands) 30 Jun 2026
OpenHands Index: testing (SWT-Bench)% resolved, higher is better 49.4% 26 of 34 GLM-4.7 (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.

SimpleQA Verified (Epoch AI) · reported by SimpleQA Verified (Epoch AI) · 1 result
MeasureValueRankConfigurationDated
SimpleQA Verified: correct answers% of questions, higher is better 32.2% 62 of 85 GLM-4.7 27 Aug 2026

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

UGI Leaderboard · reported by UGI Leaderboard · 6 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 28.0% 251 of 379 GLM-4.7 (no reasoning) 22 Dec 2025
UGI: requested-length error% off the requested word count, lower is better 33.0% 276 of 379 GLM-4.7 (thinking reasoning) 22 Dec 2025
UGI: style adherencescore from 0 to 1, higher is better 0.37 112 of 379 GLM-4.7 (no reasoning) 22 Dec 2025
UGI: style adherencescore from 0 to 1, higher is better 0.38 71 of 379 GLM-4.7 (thinking reasoning) 22 Dec 2025
UGI: writing scorescore out of 100, higher is better 44.2 190 of 379 GLM-4.7 (no reasoning) 22 Dec 2025
UGI: writing scorescore out of 100, higher is better 47.4 176 of 379 GLM-4.7 (thinking reasoning) 22 Dec 2025

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 99.8% 34 of 108 GLM-4.7 22 Sep 2026
Vectara: hallucination rate% of summaries, lower is better 11.7% 75 of 108 GLM-4.7 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 $2,377 44 of 63 GLM-4.7 1 Oct 2026

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

Will GLM-4.7 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.