Anthropic · Claude 5
Claude Fable 5
Original Fable-tier Claude (Jun 2026), now a legacy model superseded by Claude Fable 5.1.
- AA Intelligence
- 49.6#5 of 142
- Input / output per 1M
- $10.00/ $50.00
- Output speed
- 70tok/s
- Context window
- 1M tokens
Composite indexes
- 50
Leader: Claude Opus 5.5 at 58
Coding
- SciCode#3 of 9461%
Leader: Claude Opus 5.5 at 66.9%
- Terminal-Bench 4.0#6 of 8844.5%42.4%
Leader: Claude Mythos 5.1 at 60.9%
- Terminal-Bench 2.x#16 of 10384.6%
Leader: Claude Fable 5.1 at 91.4%
- SWE-bench Pro#3 of 3180%
Leader: Claude Opus 5.5 at 89.9%
Agents and tool use
Reasoning and knowledge
- GPQA Diamond#20 of 14292.6%
Leader: GPT-6 Astra at 96.1%
- Humanity’s Last Exam#4 of 14763.8%57.8%55.5%
Leader: Claude Opus 5.5 at 61.4%
- CritPt#8 of 13928.6%
Leader: GPT-5.6 Sol at 32.3%
- ARC-AGI-2#6 of 2589.2%
Leader: GPT-6 Astra at 95%
Vision and long context
- AA Long Context Reasoning#17 of 13982.3%
Leader: Kimi K3 at 88.7%
Human preference
- LMArena Text#1 of 541506
Leader: Claude Fable 5 at 1506
- LMArena WebDev#12 of 541627
Leader: Claude Opus 5.5 at 1818