Noometry

Z.ai (Zhipu), open weights

GLM-4.7-Flash

GLM-4.7-Flash by Z.ai (Zhipu) ranks 180th of 354 ranked models on the Noometry Index as of October 2026, with a score of 38.8. Its strongest category is coding, where it ranks 135th. API pricing starts at $0.06 per million input tokens and $0.40 per million output tokens, with a 200K-token context window.

Last verified

Noometry rank
#180 of 354
Index score
38.8
Evidence
Confirmed 21 results
Provider
Z.ai (Zhipu)
Released
January 19, 2026
Weights
Open weights
Reasoning
Yes
Context window
200K
Max output
131K
Input price
$0.06 / M
Output price
$0.40 / M
Blended price
$0.15 / M
Output speed
Not measured
Value
#25 of 219
Knowledge cutoff
April 2025
Input
text
Hugging Face
zai-org/GLM-4.7-Flash

Category scores

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

  1. Coding 40.6
  2. Reasoning 20.9
  3. Math 36.1
  4. Knowledge 35.5
  5. Multilingual 46.5
  6. Instruction Following 70.1
  7. Long Context 40.9
  8. Writing & Preference 47.4
CategoryScoreRankResults
Coding40.6#1351
Reasoning20.9#2292
Math36.1#1732
Knowledge35.5#1843
Multilingual46.5#1581
Instruction Following70.1#1671
Long Context40.9#1481
Writing & Preference47.4#2104

Strengths and weaknesses

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

Strongest categories

CategoryScorevs medianRank
Coding40.6+1.9#135 of 340, top 40%
Long Context40.9−0.0#148 of 296, top 50%
Math36.1−0.4#173 of 327, top 53%

Weakest categories

CategoryScorevs medianRank
Writing & Preference47.4−6.3#210 of 312, top 68%
Reasoning20.9−2.7#229 of 350, top 66%
Knowledge35.5−1.9#184 of 314, top 59%

Closest competitors

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

ModelRankScoreBlended $/MSpeed
Mistral Large 3#17639.1$0.387Compare
GLM-4.5-Air#17738.9$0.43160Compare
MiniMax-M2.1#17838.9$0.52—Compare
Qwen3-30B-A3B#17938.9$0.2142Compare
Qwen2.5 Plus 1127#18138.8——Compare
Qwen3.6 Flash#18238.8$0.42—Compare
Olmo 3 32b Think#18338.7——Compare
Hunyuan Large 2025 02 10#18438.6——Compare

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 Coding1383#146 of 294, top 50%LMArena2026-10-08

Reasoning

BenchmarkScorePositionSettingSourceDate
Chess Puzzles0%#114 of 129, top 89%Epoch AI2026-08-28
Chess Puzzles0%noneEpoch AI2026-08-28
LMArena Hard Prompts1356#156 of 297, top 53%LMArena2026-10-08

Math

BenchmarkScorePositionSettingSourceDate
OTIS Mock AIME 2024-202558.3%#104 of 173, top 61%Epoch AI2026-08-30
OTIS Mock AIME 2024-202525%noneEpoch AI2026-08-28
LMArena Math1355#162 of 285, top 57%LMArena2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond60.5%#114 of 186, top 62%Epoch AI2026-08-30
GPQA Diamond45.1%noneEpoch AI2026-08-30
Vectara Hallucination Rate (lower is better)9.3%#45 of 96, top 47%Vectara Hallucination Leaderboard
LMArena Expert1357#151 of 273, top 56%LMArena2026-10-08

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1330#158 of 297, top 54%LMArena2026-10-08
LMArena Chinese1403#138 of 285, top 49%LMArena2026-10-08
LMArena French1332#151 of 223, top 68%LMArena2026-10-08
LMArena German1337#140 of 231, top 61%LMArena2026-10-08
LMArena Korean1283#137 of 213, top 65%LMArena2026-10-08
LMArena Russian1332#157 of 283, top 56%LMArena2026-10-08
LMArena Spanish1350#144 of 226, top 64%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1327#160 of 298, top 54%LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1345#154 of 291, top 53%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1351#158 of 297, top 54%LMArena2026-10-08
LMArena Creative Writing1297#168 of 295, top 57%LMArena2026-10-08
EQ-Bench Creative Writing1125#93 of 115, top 81%EQ-Bench
LMArena Multi-Turn1342#159 of 295, top 54%LMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
bedrock$0.07$0.40—2026-10-10
deepinfra$0.06$0.40$0.012026-10-10
openrouter$0.0605$0.40—2026-10-10

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

Compare GLM-4.7-Flash

Other Z.ai (Zhipu) models

Frequently asked questions

How good is GLM-4.7-Flash?

GLM-4.7-Flash by Z.ai (Zhipu) ranks 180th of 354 ranked models on the Noometry Index as of October 2026, with a score of 38.8. Its strongest category is coding, where it ranks 135th. API pricing starts at $0.06 per million input tokens and $0.40 per million output tokens, with a 200K-token context window.

How much does GLM-4.7-Flash cost?

GLM-4.7-Flash costs $0.06 per million input tokens and $0.40 per million output tokens on deepinfra, with cached input at $0.01.

What is GLM-4.7-Flash's context window?

GLM-4.7-Flash accepts up to 200K tokens of input and can write up to 131K tokens in one response.

Is GLM-4.7-Flash open source?

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

What are GLM-4.7-Flash's strengths and weaknesses?

Relative to other ranked models, GLM-4.7-Flash places best in coding, long context, math and lowest in writing & preference, reasoning, knowledge.

What is GLM-4.7-Flash best at?

Its best category is coding, where it ranks 135th on Noometry.