AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com
#349

GLM 4.7 Flash

Z.ai Release: 2026-01-19 Tested on: 2026-10-01 00:17 z-ai/glm-4.7-flash::medium
30B total (3B active)MoEOpen source
(medium) (none)

Summary

GLM 4.7 Flash scores 4.2 on AI BENCHY and ranks #349. It has 9.4 reliability, a 30.4% pass rate, $0.193 total cost, and 150.90s average response time.

What makes GLM 4.7 Flash unique: It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.

Model facts

Researched on 2026-08-12

Reported
Parameters
30B total (3B active)
Architecture
MoE
Availability
Open source
License
MIT
Parameter source Availability source

Score

4.2

Consistency

7.1

Reliability

9.4

Total Cost (Current Price)

$0.193

Total Output Tokens

464,375

Total Input Tokens

228,711

Input Price

$0.061 / 1M

Output Price

$0.400 / 1M

Cache Read Price

N/A

Cache Write Price

N/A

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 19

Attempt pass rate: 30.4%

Flaky tests

8

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

150.90s

Response Time (max): 1539.97s

Response Time (total): 2414.33s

Wrong answer: 10 No answer: 3 Did not follow instructions: 2 Invalid tool call: 2 Timed out: 2

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#349 GLM 4.7 Flash

medium
No output was saved. The original provider response or failure reason is unavailable.
Cost
$0.000
Time
186.2s
Tokens
12,112 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-10-01 00:17 Re-test 4.2 9.4 $0.193 Current run
2026-07-16 22:32 New test added 4.3 7.8 $0.166 Compare
2026-06-04 13:29 New test added 4.4 6.7 $0.054 Compare
2026-05-21 23:50 Suite changed 4.5 8.3 $0.054 Compare
2026-04-11 01:19 First recorded run 4.6 N/A $0.046 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Run comparison

RunBenchmark coverageScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-10-01 00:17 · Current run69/69 attempts4.27.19.44/238464,375228,711$0.193150.90s
2026-04-11 01:19 · First recorded run54/54 attempts4.66.3N/A4/188112,0890$0.04632.33s
Difference—-0.4+0.800+352286+228711+$0.148+118564ms

Benchmark coverage differs: 69/69 attempts (Target: 3 repeats per test) versus 54/54 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price Cache Read Price Cache Write Price
2026-08-14 12:51 $0.060 / 1M $0.400 / 1M N/A N/A
2026-09-08 21:53 $0.061 / 1M $0.400 / 1M N/A N/A

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

GLM 4.7 FlashmediumvsMiniMax M2.5mediumGLM 4.7 Flashmediumvsgpt-oss-120bnoneGLM 4.7 FlashmediumvsMercury 2noneGLM 4.7 FlashmediumvsMercury 2.5noneGLM 4.7 FlashmediumvsCobuddymediumFree AvailableGLM 4.7 FlashmediumvsQwen3.5-9BmediumGLM 4.7 FlashmediumvsGranite 4.2 8BnoneGLM 4.7 FlashmediumvsLing 3.0 TinynoneGLM 4.7 FlashmediumvsTrinity Large PreviewnoneFree AvailableGLM 4.7 FlashmediumvsGranite 4.1 8bnone

Category Breakdown

Category Score Consistency Tests Correct
Agentic 3.9 9.6
Anti-AI Tricks 4.7 5.9
Coding 3.2 7.4
Combined 2.9 6.0
Data parsing and extraction 6.3 10.0
Domain specific 3.5 4.4
General Intelligence 3.6 9.7
Instructions following 6.2 5.8
Puzzle Solving 2.9 7.2
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models