正在读取模型档案与评测数据…
正在读取模型档案与评测数据…
Anthropic·5 个数据来源·更新于 2026-09-26
只在同一来源、同一口径下比较。切换来源可查看不同测试结果。
当前配置：各基准设置见下表
综合分数和同榜图表来自 LLM Stats 榜单（采集于 2026-09-25）；下方逐项成绩来自模型页。榜单出处
LLM Stats Score · 同一来源与榜单口径，分数越高越好
| 模型与配置 | LLM Stats Score | 每任务成本 |
|---|---|---|
| Claude Fable 5.1 | 54.5 | 未公布 |
| GPT-5.6 Sol | 54.4 | 未公布 |
| Claude Mythos Preview | 54.3 | 未公布 |
| Claude Fable 5 · 当前模型 | 54 | 未公布 |
| Muse Spark 1.3 | 53.8 | 未公布 |
| Kimi K3 | 52.5 | 未公布 |
| GLM-5.3 | 52.1 | 未公布 |
不同来源的分数不能直接相加或横向比较；评测任务成本不是 API Token 单价。
19 项已收录成绩 · 保留原始单位和测试条件
Zapier AutomationBench private held-out set at max effort. End-to-end business workflows across simulated company APIs.
成绩出处Hard subset: 46.1%. Human-solved subset: 83.9%. Blocking safeguards cause Fable 5 to perform closer to Opus 4.8 due to fallbacks. System card reports this as a Mythos 5 or combined launch-table score rather than a separate Fable-only production score; Fable may fall back to Opus 4.8 when safeguards trigger.
成绩出处DeepSWE v1.1 leaderboard, mini-swe-agent harness, max effort; Pass@1 70% ± 4%.
成绩出处Cybersecurity capture rate (Cap%). Blocking safeguards cause Fable 5 to perform closer to Opus 4.8 due to fallbacks; score reflects Claude Mythos 5. System card reports this as a Mythos 5 or combined launch-table score rather than a separate Fable-only production score; Fable may fall back to Opus 4.8 when safeguards trigger.
成绩出处FrontierCode Main subset at xhigh reasoning effort. Score 46.3%, pass rate 48.8%; Fable 5 ranks #1 and outperforms every other model even at medium effort.
成绩出处FrontierCode 1.1 current leaderboard; mergeability score at xhigh effort: 53.5%.
成绩出处Health evaluation. Blocking safeguards cause Fable 5 to perform closer to Opus 4.8 due to fallbacks. System card reports this as a Mythos 5 or combined launch-table score rather than a separate Fable-only production score; Fable may fall back to Opus 4.8 when safeguards trigger.
成绩出处Multidisciplinary reasoning. With tools: 64.5%. Without tools: 59.0%. Blocking safeguards cause Fable 5 to perform closer to Opus 4.8 on some questions due to fallbacks. System card reports this as a Mythos 5 or combined launch-table score rather than a separate Fable-only production score; Fable may fall back to Opus 4.8 when safeguards trigger.
成绩出处Fable 5 production-safeguarded configuration. OSWorld score reflects the updated harness with zoom-tool bug fix and 128K max tokens per turn.
成绩出处Fable 5 production-safeguarded configuration on SWE-Bench Pro; average over 5 trials with thinking blocks included. Mythos 5 scored 80.3%.
成绩出处Fable 5 production-safeguarded configuration on the 500-problem SWE-Bench Verified subset; average over 5 trials with thinking blocks included. Mythos 5 scored 95.5%.
成绩出处Fable 5 production-safeguarded configuration on the mini-SWE-agent harness, high effort, 89 tasks x 5 attempts. 20.9% of trials hit a safety refusal and fell back to Claude Opus 4.8 for the rest of the trajectory; Mythos 5 scored 88.0%.
成绩出处Terminal-Bench 4.0 public leaderboard; resolution rate 44.5% ± 3.8%; Claude Code agent; max effort.
成绩出处只展示有可靠来源的资料；优先采用厂商官网与官方模型仓库。
美元 / 百万 Token。不同服务商或测试配置的报价分别列出。
| 来源 / 服务商 | 输入 | 输出 | 缓存读取 |
|---|---|---|---|
| Anthropic | $10 | $50 | $1 |
| DeepInfra | $10 | $50 | 待补充 |
同名模型通过开发机构和明确版本关联。预览版、日期版本和不同规模模型分别建档。
公开评测数据；保留来源原始口径
公开模型页与公开榜单；自报成绩单独标识
公开评测数据；保留来源原始口径
Arena 官方公开数据集 · CC BY 4.0
公开模型目录与 API 报价
| 来源 / 配置 | 采集时间 | 原始数据 |
|---|---|---|
| Artificial AnalysisClaude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)SHA-256 5beb2f0dcdc468c1… | 2026-09-26T00:27:47Z | 查看来源 |
| LLM StatsClaude Fable 5 | 2026-09-25T19:40:20Z | 查看来源 |
| LLM StatsClaude Fable 5SHA-256 e63a0b107a851dd0… | 2026-09-26T00:29:15Z | 查看来源 |
| BenchLMClaude Fable 5 | 2026-09-24 | 查看来源 |
| Arenaclaude-fable-5 | 2026-09-25T19:40:08Z | 查看来源 |
| Arenaclaude-fable-5 | 2026-09-25T19:40:08Z | 查看来源 |
| Arenaclaude-fable-5 | 2026-09-25T19:40:08Z | 查看来源 |
| ArenaClaude Fable 5 (High) | 2026-09-25T19:40:08Z | 查看来源 |
| OpenRouterClaude Fable 5SHA-256 4c26b1452fbd2acd… | 2026-09-26T00:28:52Z | 查看来源 |
