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
Each axis is a category average, normalized to a 100-point radar.
Relative edge: 数学推理 +19.4 / Relative gap: none clear
Relative edge: none clear / Relative gap: 数学推理 -19.4
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 · 81.96
Best single
Claude Fable 5 · SWE-bench Verified 95.00
Modality coverage
Claude Fable 5 · 2 modalities
Head to head
12
Benchmarks
11
Wins
1
Losses
+8.47
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.
12 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Claude Fable 5 | Claude Opus 4.8 |
|---|---|---|
HLE 综合评估 | 59.00Deep Thinking Mode | 57.90Extended Thinking ｜ Tools |
LiveBench 综合评估 | 78.31Deep Thinking Mode | 78.79Deep Thinking Mode |
DeepSWE 编程与软件工程 | 70.00Deep Thinking Mode ｜ Tools | 59.00Deep Thinking Mode ｜ Tools |
SWE-Bench Pro - Public 编程与软件工程 | 80.30Deep Thinking Mode ｜ Tools | 69.20Extended Thinking ｜ Tools |
SWE-bench Verified 编程与软件工程 | 95.00Thinking Level · High ｜ Tools | 88.60Extended Thinking ｜ Tools |
WeirdML v2 编程与软件工程 | 87.85Thinking Level · High ｜ Tools | 82.89Thinking Level · Extra High ｜ Tools |
SimpleBench 常识推理 | 81.90Standard Mode | 64.80Standard Mode |
MCP-Atlas AI Agent - 工具使用 | 83.30Standard Mode ｜ Tools | 82.20Thinking Level · High ｜ Tools |
OSWorld-Verified AI Agent - 工具使用 | 85.00Thinking Level · High ｜ Tools | 83.40Extended Thinking ｜ Tools |
Terminal-Bench 2.1 AI Agent - 工具使用 | 88.00Thinking Level · High ｜ Tools | 78.90Thinking Level · High ｜ Tools |
87.80Thinking Level · High | 56.10Thinking Level · High | |
FrontierMath v2 数学推理 | 87.02Thinking Level · High | 80.00Thinking Level · High |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Claude Fable 5Anthropic | Claude Opus 4.8Anthropic |
|---|---|---|
Core specsRelease | 2026-06-09 | 2026-05-28 |
Context length | 1M | 1M |
Max output | 128000 | 128000 |
MoE | No | No |
LicenseCode Open Source | Not provided | Not provided |
Weights Open Source | Not provided | Not provided |
Commercial use | 不开源 | 不开源 |
Modality supportText Input/Output | / | / |
Image Input/Output | / | / |
ResourcesPaper / report | Claude Fable 5 and Claude Mythos 5 | Introducing Claude Opus 4.8 |
DataLearner blog | Not provided | Anthropic发布Claude Opus 4.8：定价不变，编程与智能体能力小幅提升， |
Claude Opus 4.8
Anthropic
