Advertise here
#127

GLM 5.3 FlashX Legal

Z.ai Release: 2026-11-02 Tested on: 2026-11-10 00:58 z-ai/glm-5.3-flashx-legal::high
~320B total (~18B active)MoEClosedEstimated
(max) (high) (low)

Summary

GLM 5.3 FlashX Legal scores 8.2 on AI BENCHY and ranks #127. It has 9.7 reliability, a 72.5% pass rate, $0.521 total cost, and 35.19s average response time.

Model facts

Researched on 2026-11-09

Estimated
Parameters
~320B total (~18B active)
Architecture
MoE
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. Z.ai's legal-domain variant of GLM-5.3-FlashX with extra legal mid-training and RL post-training; no weights are published. Counts are inherited from the FlashX record (320B total / 18B active MoE) because domain post-training is not reported to change the backbone.

Parameter source 1 Parameter source 2 Availability source

Score

8.2

Consistency

8.6

Reliability

9.7

Total Cost (Current Price)

$0.521

Total Output Tokens

345,985

Total Input Tokens

238,713

Input Price

$0.370 / 1M

Output Price

$1.250 / 1M

Cache Read Price

$0.075 / 1M

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: 8

Attempt pass rate: 72.5%

Flaky tests

4

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

Response Time (avg)

35.19s

Response Time (max): 298.81s

Response Time (total): 809.47s

Wrong answer: 4 No answer: 2 Did not follow instructions: 1 Invalid tool call: 1

Hamster playing table tennis

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

#127 GLM 5.3 FlashX Legal

high
Cost
$0.018
Time
103.8s
Tokens
13,703 tok

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 5.3 FlashX LegalhighvsGPT-5.6 TerramediumGLM 5.3 FlashX LegalhighvsSeed-2.0-LitemediumGLM 5.3 FlashX LegalhighvsGLM 5.2mediumGLM 5.3 FlashX LegalhighvsKimi K3.1 ProhighGLM 5.3 FlashX LegalhighvsGrok 4.5highGLM 5.3 FlashX LegalhighvsSeed-2.0-CodelowGLM 5.3 FlashX LegalhighvsDeepSeek V4.1 Flash 1017maxGLM 5.3 FlashX LegalhighvsDeepSeek V4 Pro 0423highGLM 5.3 FlashX LegalhighvsGemini 4 ArgonlowGLM 5.3 FlashX LegalhighvsClaude Opus 4.7medium

Category Breakdown

Category Score Consistency Tests Correct
Agentic 10.0 10.0
Anti-AI Tricks 8.2 7.9
Coding 8.2 7.2
Combined 6.9 5.9
Data parsing and extraction 10.0 10.0
Domain specific 3.0 10.0
General Intelligence 4.8 3.2
Instructions following 10.0 10.0
Puzzle Solving 10.0 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models