#63 GLM 5.3 FlashX
max- Cost
- $0.046
- Time
- 251.3s
- Tokens
- 36,769 tok
Z.ai
Release: 2026-09-21
Tested on: 2026-09-21 21:14
z-ai/glm-5.3-flashx::max
320B total (18B active)MoEClosed
Summary
GLM 5.3 FlashX scores 8.3 on AI BENCHY and ranks #63. It has 10.0 reliability, a 78.8% pass rate, $0.508 total cost, and 41.21s average response time.
Model facts
Researched on 2026-09-21
- Parameters
- 320B total (18B active)
- Architecture
- MoE
- Availability
- Closed
- License
- -
OpenRouter reports 320B total and 18B active parameters for FlashX. This record describes the hosted FlashX checkpoint; the open Flash weights do not establish an exact FlashX weights release.
8.3
Consistency
8.3
10.0
$0.508
Total Output Tokens
375,734
Total Input Tokens
101,211
Input Price
$0.370 / 1M
Output Price
$1.250 / 1M
Flaky tests
5
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
GLM 5.3 FlashXmaxvsInkling SmallhighGLM 5.3 FlashXmaxvsDeepSeek V4.1 FlashmaxGLM 5.3 FlashXmaxvsSeed 2.1 TurbomediumGLM 5.3 FlashXmaxvsMuse Spark 1.1lowGLM 5.3 FlashXmaxvsQwen3.8 27BhighGLM 5.3 FlashXmaxvsClaude Fable 5.1mediumGLM 5.3 FlashXmaxvsGPT-5.2mediumGLM 5.3 FlashXmaxvsGemini 2.5 FlashmediumGLM 5.3 FlashXmaxvsGrok 4.5lowGLM 5.3 FlashXmaxvsMuse Spark 1.3low
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 10.0 | 10.0 | |
| Coding | 8.2 | 7.2 | |
| Combined | 8.2 | 6.9 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 3.5 | 4.4 | |
| General Intelligence | 10.0 | 10.0 | |
| Instructions following | 9.9 | 10.0 | |
| Puzzle Solving | 8.2 | 7.7 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |