See key specs and per-benchmark scores for each model/mode. Scroll horizontally for all columns. 当前对比 2 个模型的评测数据与核心参数。
Claude Fable 5
Anthropic
GLM-5.2
智谱AI
Each axis is a category average, normalized to a 100-point radar.
Relative edge: 数学推理 +43.2 / Relative gap: none clear
Relative edge: none clear / Relative gap: 数学推理 -43.2
Method: for each model and benchmark, the chart first averages all scores in the current mode scope instead of taking the best score, then averages those benchmark scores within each category. Only benchmarks with at least two selected models scored are included; missing values are not counted as zero.
Best overall
Claude Fable 5 · 80.35
Best single
Claude Fable 5 · Terminal-Bench 2.1 88.00
Modality coverage
Claude Fable 5 · 2 modalities
Head to head
10
Benchmarks
10
Wins
0
Losses
+19.41
Average diff
Compare benchmark results across thinking modes and tool usage.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Complete scores for each model/mode across selected benchmarks.
10 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Claude Fable 5 | GLM-5.2 |
|---|---|---|
HLE 综合评估 | 59.00Deep Thinking Mode | 54.70Thinking Enabled ｜ Tools |
LiveBench 综合评估 | 78.31Deep Thinking Mode | 76.24Standard Mode |
DeepSWE 编程与软件工程 | 70.00Deep Thinking Mode ｜ Tools | 44.00Deep Thinking Mode ｜ Tools |
SWE-Bench Pro - Public 编程与软件工程 | 80.30Deep Thinking Mode ｜ Tools | 62.10Thinking Enabled ｜ Tools |
WeirdML v2 编程与软件工程 | 87.85Thinking Level · High ｜ Tools | 67.31Thinking Level · High ｜ Tools |
SimpleBench 常识推理 | 81.90Standard Mode | 58.80Standard Mode |
MCP-Atlas AI Agent - 工具使用 | 83.30Standard Mode ｜ Tools | 76.80Thinking Enabled ｜ Tools |
Terminal-Bench 2.1 AI Agent - 工具使用 | 88.00Thinking Level · High ｜ Tools | 81.00Thinking Level · High ｜ Tools |
87.80Thinking Level · High | 29.27Thinking Level · High | |
FrontierMath v2 数学推理 | 87.02Thinking Level · High | 59.21Thinking Level · High |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Claude Fable 5Anthropic | GLM-5.2智谱AI |
|---|---|---|
Core specsRelease | 2026-06-09 | 2026-06-13 |
Context length | 1M | 1M |
Parameters | — | 753.3B |
Active parameters | Not provided | 40B |
Max output | 128000 | 128000 |
MoE | No | Yes |
LicenseCode Open Source | Closed Source | Open Source · MIT License |
Weights Open Source | Closed Source | Open Source · MIT License |
Commercial use | 不开源 | 免费商用授权 |
Local deploymentWeight size | Not provided | 约 1.5 TB（BF16 safetensors） |
VRAM for weights | Not provided | ≈ 1500 GB (weights only, excludes KV cache) |
Weights | Not provided | Hugging Face |
Source repo | Not provided | GitHub |
Modality supportText Input/Output | / | / |
Image Input/Output | / | Not provided |
ResourcesPaper / report | Claude Fable 5 and Claude Mythos 5 | GLM-5: from Vibe Coding to Agentic Engineering |
