GLM-5.3 Benchmark Details
GLM-5.3 currently shows benchmark results led by HLE (4 / 190, score 62.50), Creative Writing (3 / 99, score 2062.40), Terminal-Bench 2.1 (5 / 49, score 88.20). This page also compares it with 4 competitor models and 4 predecessor or same-series models, including performance and pricing views when available.
Benchmark Results
Benchmark Results
Writing and Creative Capabilities
1 evaluationsText Embedding
3 evaluationsAI Agent - Tool Usage
10 evaluationsCoding and Software Engineer
6 evaluationsMath and Reasoning
2 evaluationsCompetitor Comparison
Benchmark scores for GLM-5.3 compared against top models in its class
12 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | GLM-5.3Current | Kimi K3 | Claude Opus 5 | GPT-5.6 Sol | DeepSeek-V4-Pro |
|---|---|---|---|---|---|
HLE 综合评估 | 62.50Thinking Level · High ｜ Tools | 56.00Thinking Level · High ｜ Tools | 64.70Thinking Level · High ｜ Tools | 49.50Thinking Level · High | 48.20Thinking Level · Extra High ｜ Tools |
GPQA Diamond 科学与综合推理 | 90.91Thinking Level · High | 93.50Thinking Level · High | 93.88Thinking Level · High | 93.50Thinking Level · High | 90.10Thinking Level · High |
Creative Writing 写作和创作 | 2062.40Standard Mode | 2070.80Standard Mode | 2116.10Standard Mode | 1964.10Standard Mode | 1552.10Standard Mode |
SimpleBench 常识推理 | 66.20Thinking Level · High | 60.70Thinking Level · High | 80.60Thinking Level · High | 64.80Thinking Level · Extra High | 50.90Standard Mode |
Context Arena 文本向量检索 | 88.53Thinking Level · High | 71.75Thinking Level · High | 97.72Thinking Level · High | 97.63Thinking Level · High | 76.09Thinking Enabled |
AutomationBench AI Agent - 工具使用 | 48.20Thinking Level · High ｜ Tools | 30.80Thinking Level · High ｜ Tools | 26.00Thinking Level · High ｜ Tools | -- | 31.80Thinking Level · Extra High ｜ Tools |
CyberGym AI Agent - 工具使用 | 84.50Thinking Level · High ｜ Tools | -- | -- | -- | 83.30Thinking Level · Extra High ｜ Tools |
Terminal-Bench 2.1 AI Agent - 工具使用 | 88.20Thinking Level · High ｜ Tools | 88.30Thinking Level · High ｜ Tools | -- | 88.80Thinking Level · High | 87.90Thinking Level · Extra High ｜ Tools |
Terminal-Bench 3.0 AI Agent - 工具使用 | 28.30Thinking Level · High ｜ Tools | -- | -- | 34.60Thinking Level · High ｜ Tools | -- |
Terminal-Bench 4.0 AI Agent - 工具使用 | 41.82Thinking Level · High ｜ Tools | -- | 51.82Thinking Level · High ｜ Tools | 37.27Thinking Level · High ｜ Tools | -- |
Terminal-Bench-Science 0.1 AI Agent - 工具使用 | 8.10Thinking Level · High ｜ Tools | 7.10Thinking Level · High ｜ Tools | 30.00Thinking Level · High ｜ Tools | 22.40Thinking Level · High ｜ Tools | -- |
Toolathlon-Verified AI Agent - 工具使用 | 73.00Thinking Level · High ｜ Tools | 76.50Thinking Level · High ｜ Tools | -- | -- | 74.10Thinking Level · Extra High ｜ Tools |
Standard API Pricing: GLM-5.3 vs. Peer Models
Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.
Source: DataLearnerAI. Standard text prices shown here use the default supplier.
These models use different currencies or billing units, so the page falls back to raw price values instead of a shared bar chart.
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
GLM-5.3 | 智谱AI | $1.4 / 1M tokens | $4.4 / 1M tokens | — |
Kimi K3 | Moonshot AI | ¥20 / 1M tokens | ¥100 / 1M tokens | — |
Claude Opus 5 | Anthropic | $5 / 1M tokens | $25 / 1M tokens | — |
GPT-5.6 Sol | OpenAI | $4 / 1M tokens | $20 / 1M tokens | — |
DeepSeek-V4-Pro | DeepSeek-AI | $0.435 / 1M tokens | $0.87 / 1M tokens | — |
Version History
How each version of the GLM-5.3 series stacks up on benchmark tests
12 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.· Click a row to view its trend chart.
| Benchmark | GLM-5.3Current | GLM-5.2 | GLM 5.1 | GLM-5 | GLM-4.7 |
|---|---|---|---|---|---|
HLE 综合评估 | 62.50Thinking Level · High ｜ Tools | 54.70Thinking Enabled ｜ Tools | 52.30Thinking Enabled ｜ Tools | 50.40Thinking Enabled ｜ Tools | 42.80Thinking Enabled ｜ Tools |
GPQA Diamond 科学与综合推理 | 90.91Thinking Level · High | 91.86Thinking Level · High | 86.20Thinking Enabled | 86.00Thinking Enabled | 85.70Thinking Enabled |
Creative Writing 写作和创作 | 2062.40Standard Mode | 1750.90Standard Mode | 1589.20Standard Mode | 1597.60Standard Mode | 1410.50Standard Mode |
SimpleBench 常识推理 | 66.20Thinking Level · High | 58.80Standard Mode | 55.10Standard Mode | 53.20Standard Mode | 47.70Thinking Enabled |
Context Arena 文本向量检索 | 88.53Thinking Level · High | 72.34Thinking Level · High | 62.05Thinking Enabled | -- | -- |
Terminal-Bench 2.1 AI Agent - 工具使用 | 88.20Thinking Level · High ｜ Tools | 81.00Thinking Level · High ｜ Tools | 58.70Thinking Level · High ｜ Tools | -- | -- |
DeepSWE 编程与软件工程 | 66.90Thinking Level · High ｜ Tools | 44.00Deep Thinking Mode ｜ Tools | -- | -- | -- |
FrontierSWE 编程与软件工程 | 78.10Thinking Level · High ｜ Tools | 74.40Thinking Level · High ｜ Tools | -- | -- | -- |
NL2Repo-Bench 编程与软件工程 | 58.00Thinking Level · High ｜ Tools | 48.90Thinking Enabled ｜ Tools | -- | -- | -- |
PostTrain Bench 编程与软件工程 | 39.80Thinking Level · High ｜ Tools | 34.30Thinking Level · High ｜ Tools | -- | -- | -- |
Program Bench 编程与软件工程 | 19.00Thinking Level · High ｜ Tools | 63.70Thinking Enabled ｜ Tools | -- | -- | -- |
SWE-Marathon 编程与软件工程 | 42.50Thinking Level · High ｜ Tools | 13.00Thinking Level · High ｜ Tools | -- | -- | -- |
Single-Benchmark Version Trend
Viewing: HLE · 综合评估
Standard API Pricing Across the GLM-5.3 Series
Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.
Source: DataLearnerAI. Standard text prices shown here use the default supplier.
These models use different currencies or billing units, so the page falls back to raw price values instead of a shared bar chart.
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
GLM-5.3 | 智谱AI | $1.4 / 1M tokens | $4.4 / 1M tokens | — |
GLM-5.2 | 智谱AI | $1.4 / 1M tokens | $4.4 / 1M tokens | — |
GLM 5.1 | 智谱AI | $1.4 / 1M tokens | $4.4 / 1M tokens | — |
GLM-5 | 智谱AI | $1 / 1M tokens | $3.2 / 1M tokens | — |
GLM-4.7 | 智谱AI | ¥4 / 1M tokens | ¥16 / 1M tokens | — |