Claude Fable 5 vs Claude Fable 5.1

Change models
IndexAll categories, out of 100.
74.0 ±2.7
76.2 ±2.4 best
GapIndex points below the top.
−2.2 · no clear gap
Top
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
56/s
69/s best
EloLMArena rating and rank.
1492
1512 best
ReleasedMonth of release.
2026-06
2026-09
Input / 1MUS dollars per 1M input tokens.
$10.00
$10.00
Output / 1MUS dollars per 1M output tokens.
$50.00
$50.00
Batch output / 1MBatch price per 1M output tokens.
$25.00
$25.00
1K chats2K tokens in, 500 out, each.
$45.00
$45.00
1K documents20K tokens in, 1K out, each.
$250.00
$250.00
1K agent tasks200K tokens in, 20K out, each.
$3,000.00
$3,000.00
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
71.4 best
71.1
CodingCode writing and repair.
74.7
77.7 best
ReasoningLogic problems and puzzles.
73.6
75.8 best
MultimodalTasks with images and text.
70.1
77.9 best
KnowledgeFacts and expert knowledge.
75.8
77.2 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
64.1
74.3 best
MathMath problems.
76.2
77.0 best

Benchmarks

70 shared
Only Claude Fable 5: 22Only Claude Fable 5.1: 62
Claude Fable 5
Claude Fable 5.1
55.5%5 / 222
59.1% best3 / 222
82.3%27 / 217
85.3% best5 / 217
28.6%14 / 214
29.7% best12 / 214
99.7%14 / 200
100.0% best1 / 200
92.6%17 / 199
93.7% best7 / 199
65.4%4 / 164
68.4% best2 / 164
88.6% best1 / 149
88.5%2 / 149
TaxEval v2Finance
76.9% best5 / 143
76.0%8 / 143
89.8%2 / 142
90.5% best1 / 142
93.2%10 / 135
93.4% best7 / 135
MMLU ProKnowledge
91.5%3 / 135
92.4% best1 / 135
55.5%18 / 133
62.7% best6 / 133
89.2%11 / 131
90.0% best9 / 131
98.5% best1 / 126
97.5%5 / 126
90.4% best4 / 123
90.3%6 / 123
96.4%9 / 122
98.3% best2 / 122
97.6%17 / 116
99.0% best2 / 116
61.0%6 / 114
63.1% best3 / 114
MedScribeHealthcare
88.5%12 / 109
91.3% best2 / 109
MedCodeHealthcare
56.1% best4 / 106
53.5%8 / 106