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Original Fable-tier Claude (Jun 2026), now a legacy model superseded by Claude Fable 5.1.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#10 of 151
- Input / output per 1M
- $10.00/ $50.00
- Output speed
- 70tok/s
- Context window
- 1M tokens
Composite indexes
- Artificial Analysis Intelligence Index#10 of 15150
Leader: Claude Opus 5.5 at 58
Coding
- SciCode#5 of 10061%
Leader: Claude Opus 5.5 at 66.9%
- Terminal-Bench 4.0#11 of 9644.5%42.4%
Leader: Claude Sonnet 5.5 at 70.6%
- Terminal-Bench 2.x#16 of 10584.6%
Leader: Claude Fable 5.1 at 91.4%
- SWE-bench Pro#4 of 3380%
Leader: Claude Opus 5.5 at 89.9%
Agents and tool use
Reasoning and knowledge
- GPQA Diamond#20 of 14492.6%
Leader: GPT-6 Astra at 96.1%
- Humanity’s Last Exam#6 of 15363.8%57.8%55.5%
Leader: Claude Sonnet 5.5 at 64.5%
- CritPt#9 of 14428.6%
Leader: Muse Wonder Full at 33%
- ARC-AGI-2#6 of 2589.2%
Leader: GPT-6 Astra at 95%
Vision and long context
- AA Long Context Reasoning#19 of 14482.3%
Leader: Kimi K3 at 88.7%
Human preference
- LMArena Text#2 of 571506
Leader: Gemini 4 Argon at 1525
- LMArena WebDev#14 of 581627
Leader: Claude Opus 5.5 at 1818