#18Z.ai· released 2026-09-18

Z.ai: GLM 5.3 FlashX.

GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...

View on OpenRouter ↗
Context
1.0M
Input $/1M
$0.37
Output $/1M
$1.25
Modality
text · image · video
Arena Elo
1533
LMArena — human blind votes
AA Index
50.0
Artificial Analysis composite
LiveBench
77.9
Contamination-resistant
GPQA
81.9%
Grad-level science reasoning
MMLU-Pro
82.3%
Broad knowledge
SWE-bench
70.6%
Real GitHub bugs (Verified)
Terminal-Bench
52.1%
Agentic shell tasks
ARC-AGI
13.1%
Abstract reasoning
Aider Polyglot
78.8%
Multi-language code editing
Speed
195 tok/s
Median output speed

Profile

Z.ai: GLM 5.3 FlashX is Z.ai's entry at position #18 on the current aggregated leaderboard. Its strongest signals are graduate-level science reasoning, real-world software engineering, unattended agentic work, and raw output speed. Every figure below is aggregated from the public sources listed on the homepage and refreshed on each pipeline run.

The score spread is comparatively complete for this model, but the standing advice still applies: treat gaps of a few points as ties and validate on your own workload before committing.

How this model's position is computed is documented in the methodology; what each benchmark actually measures is in the benchmark guide. See a figure that disagrees with its source? Report it — accepted corrections apply on the next refresh.

Nearby on the leaderboard