Claude Fable 5.1 vs Claude Opus 5

Change models
Claude Opus 5Anthropic
IndexAll categories, out of 100.
76.2 ±2.4 best
73.8 ±1.9
GapIndex points below the top.
Top
−2.4 · no clear gap
CoverageIndex weight that has results.
95%
100% best
SpeedOutput tokens per second.
69/s best
48/s
EloLMArena rating and rank.
1512 best
1502
ReleasedMonth of release.
2026-09
2026-07
Input / 1MUS dollars per 1M input tokens.
$10.00
$5.00 best
Output / 1MUS dollars per 1M output tokens.
$50.00
$25.00 best
Batch output / 1MBatch price per 1M output tokens.
$25.00
$12.50 best
1K chats2K tokens in, 500 out, each.
$45.00
$22.50 best
1K documents20K tokens in, 1K out, each.
$250.00
$125.00 best
1K agent tasks200K tokens in, 20K out, each.
$3,000.00
$1,500.00 best
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
71.1
71.6 best
CodingCode writing and repair.
77.7 best
74.8
ReasoningLogic problems and puzzles.
75.8 best
75.4
MultimodalTasks with images and text.
77.9 best
72.5
KnowledgeFacts and expert knowledge.
77.2 best
73.1
MultilingualTasks in many languages.
—
63.6
InstructionTasks with strict prompt rules.
74.3 best
55.6
MathMath problems.
77.0 best
74.8

Benchmarks

102 shared
Only Claude Fable 5.1: 30Only Claude Opus 5: 48
Claude Fable 5.1
Claude Opus 5
59.1% best3 / 222
54.9%7 / 222
85.3% best5 / 217
79.3%52 / 217
29.7% best12 / 214
29.1%13 / 214
100.0% best1 / 200
98.9%22 / 200
93.7% best7 / 199
93.2%11 / 199
68.4% best2 / 164
60.9%7 / 164
88.5% best2 / 149
87.0%7 / 149
TaxEval v2Finance
76.0% best8 / 143
75.1%23 / 143
90.5% best1 / 142
89.0%4 / 142
93.4%7 / 135
93.4%7 / 135
MMLU ProKnowledge
92.4% best1 / 135
91.6%2 / 135
62.7% best6 / 133
61.1%7 / 133
90.0%9 / 131
90.4% best8 / 131
97.5%5 / 126
97.5%5 / 126
90.3% best6 / 123
88.4%11 / 123
98.3% best2 / 122
97.1%6 / 122
99.0%2 / 116
99.0%2 / 116
63.1% best3 / 114
56.4%26 / 114
MedScribeHealthcare
91.3% best2 / 109
91.0%4 / 109
MedCodeHealthcare
53.5%8 / 106
63.6% best1 / 106