Claude Fable 5.2 vs MiMo-V2.6-Pro

Change models
Claude Fable 5.2AnthropicSmartest
IndexAll categories, out of 100.
85.6 ±3.7 best
70.2 ±4.7
GapIndex points below the top.
Top
−15.4
CoverageIndex weight that has results.
90% best
80%
SpeedOutput tokens per second.
64/s best
31/s
EloLMArena rating and rank.
—
1492
ReleasedMonth of release.
2026-11
2026-09
Input / 1MUS dollars per 1M input tokens.
$8.00
$0.435 best
Output / 1MUS dollars per 1M output tokens.
$40.00
$0.87 best
Batch output / 1MBatch price per 1M output tokens.
$20.00
—
1K chats2K tokens in, 500 out, each.
$36.00
$1.31 best
1K documents20K tokens in, 1K out, each.
$200.00
$9.57 best
1K agent tasks200K tokens in, 20K out, each.
$2,400.00
$104.40 best
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
82.2 best
72.1
CodingCode writing and repair.
86.2 best
66.6
ReasoningLogic problems and puzzles.
86.5 best
68.3
MultimodalTasks with images and text.
82.0
—
KnowledgeFacts and expert knowledge.
87.1 best
64.2
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
79.3 best
71.3

Benchmarks

25 shared
Only Claude Fable 5.2: 46Only MiMo-V2.6-Pro: 33
Claude Fable 5.2
MiMo-V2.6-Pro
74.3% best1 / 222
49.4%14 / 222
83.3%13 / 217
86.3% best3 / 217
35.4% best1 / 214
26.6%19 / 214
79.1% best1 / 164
34.8%67 / 164
93.8% best1 / 123
85.2%16 / 123
67.7% best1 / 114
60.9%8 / 114
46.2%19 / 90
47.1% best16 / 90
32.1%23 / 82
32.4% best22 / 82
19.0% best1 / 65
0.5%19 / 65
65.2% best1 / 61
31.3%24 / 61
DeepSWEAgentic
74.3% best9 / 59
71.9%18 / 59
33.0 best1 / 54
1.525 / 54
22.0 best1 / 54
5.016 / 54
100.0% best1 / 54
70.0%21 / 54
55.7% best2 / 44
2.9%33 / 44
5.0%27 / 35
13.8% best13 / 35
51.4%11 / 32
53.1% best7 / 32
51.8% best2 / 30
15.3%28 / 30
58.0% best1 / 25
22.7%18 / 25
76.4% best3 / 23
58.6%15 / 23