Noometry

Z.ai (Zhipu), open weights

GLM-4.7

GLM-4.7 by Z.ai (Zhipu) ranks 124th of 354 ranked models on the Noometry Index as of October 2026, with a score of 42.0. Its strongest category is coding, where it ranks 79th. API pricing starts at $0.60 per million input tokens and $2.20 per million output tokens, with a 205K-token context window.

Last verified

Noometry rank
#124 of 354
Index score
42.0
Evidence
Confirmed 36 results
Provider
Z.ai (Zhipu)
Released
December 22, 2025
Weights
Open weights
Reasoning
Yes
Context window
205K
Max output
131K
Input price
$0.60 / M
Output price
$2.20 / M
Blended price
$1 / M
Output speed
Not measured
Value
#110 of 219
Knowledge cutoff
April 2025
Input
text
Hugging Face
zai-org/GLM-4.7

Category scores

Each category score combines every public result we have in that category.

  1. Coding 44.0
  2. Agentic & Tool Use 26.5
  3. Reasoning 24.3
  4. Math 38.6
  5. Knowledge 47.0
  6. Multilingual 52.8
  7. Instruction Following 74.4
  8. Long Context 42.8
  9. Writing & Preference 60.9
CategoryScoreRankResults
Coding44.0#793
Agentic & Tool Use26.5#1031
Reasoning24.3#1644
Math38.6#1353
Knowledge47.0#804
Multilingual52.8#791
Instruction Following74.4#951
Long Context42.8#1163
Writing & Preference60.9#934

Strengths and weaknesses

Categories where GLM-4.7 places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Coding44.0+5.2#79 of 340, top 24%
Knowledge47.0+9.7#80 of 314, top 26%
Multilingual52.8+5.4#79 of 297, top 27%

Weakest categories

CategoryScorevs medianRank
Agentic & Tool Use26.5−3.8#103 of 154, top 67%
Reasoning24.3+0.7#164 of 350, top 47%
Math38.6+2.0#135 of 327, top 42%

Closest competitors

The models ranked just above and below GLM-4.7. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
Longcat Flash Chat#12042.1—69Compare
Solar Pro4#12142.1$0.52—Compare
GLM-4.5#12242.0$132Compare
Qwen3.5 35B-A3B#12342.0$0.69—Compare
GPT-5.4 nano#12541.9$0.4619Compare
Amazon Nova Experimental Chat 10 09#12641.9——Compare
Qwen3.5 27B#12741.9$0.82—Compare
GPT-5 Mini#12841.8$0.693Compare

Sponsored placements are available on pages like this one. Advertise on Noometry

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
LMArena WebDev1435#62 of 113, top 55%LMArena2026-10-08
SciCode45.1%#59 of 121, top 49%Epoch AI
LMArena Coding1454#79 of 294, top 27%LMArena2026-10-08
ALE-Bench399.48#90 of 105, top 86%Epoch AI

Agentic & Tool Use

BenchmarkScorePositionSettingSourceDate
Terminal-Bench33.4%#30 of 41, top 74%Epoch AI
Vending-Bench 22,377#42 of 60, top 70%Epoch AI

Reasoning

BenchmarkScorePositionSettingSourceDate
SimpleBench47.7%#42 of 77, top 55%Epoch AI
SimpleBench47.7%#42 of 77, top 55%Epoch AI
CritPt1.7%#74 of 134, top 56%Epoch AI
Chess Puzzles6%#89 of 129, top 69%Epoch AI2026-01-29
LMArena Hard Prompts1443#78 of 297, top 27%LMArena2026-10-08
Epoch Capabilities Index143.51#91 of 213, top 43%Epoch AI2025-12-22

Math

BenchmarkScorePositionSettingSourceDate
OTIS Mock AIME 2024-202583.3%#75 of 173, top 44%Epoch AI2026-01-29
ProofBench6%#67 of 77, top 88%Epoch AI
LMArena Math1423#97 of 285, top 35%LMArena2026-10-08
FrontierMath (Feb 2025 set)2.4%#53 of 68, top 78%Epoch AI2026-01-30
FrontierMath Tier 4 (v1)0%#49 of 55, top 90%Epoch AI2026-01-30

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond83.3%#71 of 186, top 39%Epoch AI2026-01-29
SimpleQA Verified32.2%#55 of 77, top 72%Epoch AI2026-08-27
Vectara Hallucination Rate (lower is better)11.7%#69 of 96, top 72%Vectara Hallucination Leaderboard
LMArena Expert1424#103 of 273, top 38%LMArena2026-10-08

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1417#79 of 297, top 27%LMArena2026-10-08
LMArena Chinese1495#50 of 285, top 18%LMArena2026-10-08
LMArena French1432#89 of 223, top 40%LMArena2026-10-08
LMArena German1424#72 of 231, top 32%LMArena2026-10-08
LMArena Japanese1439#30 of 211, top 15%LMArena2026-10-08
LMArena Korean1399#55 of 213, top 26%LMArena2026-10-08
LMArena Russian1423#77 of 283, top 28%LMArena2026-10-08
LMArena Spanish1434#74 of 226, top 33%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1411#85 of 298, top 29%LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
CL-bench15.9%#14 of 19, top 74%Epoch AI
CL-bench Life10.9%#10 of 13, top 77%Epoch AI
LMArena Longer Query1432#76 of 291, top 27%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1435#72 of 297, top 25%LMArena2026-10-08
LMArena Creative Writing1401#81 of 295, top 28%LMArena2026-10-08
EQ-Bench Creative Writing1413#68 of 115, top 60%EQ-Bench
LMArena Multi-Turn1446#62 of 295, top 22%LMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
bedrock$0.60$2.20—2026-10-10
deepinfra$0.40$1.75$0.082026-10-10
openrouter$0.60$2.20$0.112026-10-10
vertex$0.60$2.20$0.062026-10-10
zai$0.60$2.20$0.112026-10-10

All Z.ai (Zhipu) API prices → Estimate your cost →

Compare GLM-4.7

Other Z.ai (Zhipu) models

Frequently asked questions

How good is GLM-4.7?

GLM-4.7 by Z.ai (Zhipu) ranks 124th of 354 ranked models on the Noometry Index as of October 2026, with a score of 42.0. Its strongest category is coding, where it ranks 79th. API pricing starts at $0.60 per million input tokens and $2.20 per million output tokens, with a 205K-token context window.

How much does GLM-4.7 cost?

GLM-4.7 costs $0.60 per million input tokens and $2.20 per million output tokens on Z.ai (Zhipu)'s own API, with cached input at $0.11.

What is GLM-4.7's context window?

GLM-4.7 accepts up to 205K tokens of input and can write up to 131K tokens in one response.

Is GLM-4.7 open source?

Yes. GLM-4.7's weights are downloadable from Hugging Face (zai-org/GLM-4.7); check the license for commercial terms.

What are GLM-4.7's strengths and weaknesses?

Relative to other ranked models, GLM-4.7 places best in coding, knowledge, multilingual and lowest in agentic & tool use, reasoning, math.

What is GLM-4.7 best at?

Its best category is coding, where it ranks 79th on Noometry.