GLM-5.3
GLM-5.3 is Z.AI’s Frontier coding flagship from August 14, 2026, with 744 billion total and 40 billion active parameters. All improvements over GLM-5.2 stem from post-training: Terminal-Bench 3.0 rose from 4.6 to 28.3 percent, ExploitBench more than doubled. Reasoning is mandatorily active, context one million tokens. Weights available since 08/28/2026 under the bespoke GLM-5.3 license (MIT-like, $10B MaaS security review gate); Chinese cloud infrastructure.
- Restricted Weights
- Server
- OpenRouter
- Text
- Agentic Orchestrator
- Long Context
- Batch
Sovereign Risk: HIGH The developer Z.AI is headquartered in China. The model’s development is therefore subject to Chinese legislation, which represents an elevated risk in the international context with regard to data security and state influence. As of the current date (August 23, 2026), the weights have not yet been released; the model is exclusively available via the GLM Coding Plan and the Z.AI cloud infrastructure, meaning all requests are routed through Chinese servers. Risk mitigation through local deployment is not currently possible.
Key metrics
Score · Latency · Cost · Quality
- Total Score Gold
- 82.25
- Routine
- 50.63
- Reasoning
- 31.62
- LLM Judge Avg
- 4.18 / 5
- 100 Coverage
- Avg Task Duration
- 58.51s
- Batch
- Token Rate
- 136.97tok/s
- Output Rate
- P95 Latency
- 207.18s
- Top 5 %
- Total Tokens
- 357300
- Output Volume
- Cost per 1K
- $0.0044
- USD / 1K Requests
- Benchmark Cost
- $1.57
- Total · 357300 tok
Benchmark modules
10 modules · weighted · vs. model median & top performer
Token efficiency & latency
Consumption per module vs. model median
Token consumption per module
Performance profile
Key metrics – legend
Score
- Total Score
- Overall score derived from Routine and Reasoning scores. Basis for the fleet rank and tier assignment (Gold / Silver / Bronze / Standard).
- Routine
- Score for standard tasks: code generation, text transformation, structured outputs. Weighted by task complexity.
- Reasoning
- Score for analytical and logical tasks: multi-step problem solving, mathematical reasoning, structured argumentation.
- Rank
- Position in the fleet comparison, sorted by Total Score. Refers to the snapshot at the time of testing.
LLM Judge
- LLM Judge Ø
- Average quality rating by an independent judge model on a scale of 1–5.
- Coverage
- Share of tasks for which a judge rating is available. 100% means all responses were evaluated.
Latency & speed
- Avg. Task Duration
- Average time per task from the first to the last token of the response, measured across all benchmark tasks.
- Token Rate
- Output speed in tokens per second. Relevant for interactive applications and real-time streaming.
- P95 Latency
- 95th percentile of response times — shows outliers. Lower values mean fewer long wait times in edge cases.
Cost
- Cost per 1K
- API price per 1,000 output tokens in US dollars. Basis for cost calculation in production use.
- Benchmark Cost
- Total cost for the complete benchmark run of this model.