Claude Fable 5.2 vs Gemini 4 Neon

Change models
Claude Fable 5.2AnthropicSmartest
IndexAll categories, out of 100.
84.0 ±3.5 best
81.9 ±4.4
GapIndex points below the top.
Top
−2.1 · no clear gap
CoverageIndex weight that has results.
90%
90%
SpeedOutput tokens per second.
86/s
110/s best
EloLMArena rating and rank.
1478
1524 best
ReleasedMonth of release.
2026-11
2026-11
Input / 1MUS dollars per 1M input tokens.
$8.00
$3.00 best
Output / 1MUS dollars per 1M output tokens.
$40.00
$15.00 best
Batch output / 1MBatch price per 1M output tokens.
$20.00
$7.50 best
1K chats2K tokens in, 500 out, each.
$36.00
$13.50 best
1K documents20K tokens in, 1K out, each.
$200.00
$75.00 best
1K agent tasks200K tokens in, 20K out, each.
$2,400.00
$900.00 best
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
81.3 best
81.2
CodingCode writing and repair.
83.6 best
83.5
ReasoningLogic problems and puzzles.
84.9
87.7 best
MultimodalTasks with images and text.
80.1 best
72.7
KnowledgeFacts and expert knowledge.
87.2 best
78.3
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
77.7 best
75.9

Benchmarks

23 shared
Only Claude Fable 5.2: 53Only Gemini 4 Neon: 1
Claude Fable 5.2
Gemini 4 Neon
94.9%10 / 220
96.3% best5 / 220
99.7%17 / 203
100.0% best1 / 203
79.1% best1 / 170
60.5%10 / 170
94.0% best1 / 94
75.2%6 / 94
Chess PuzzlesReasoning
79.0%2 / 93
83.0% best1 / 93
95.1% best1 / 93
91.2%5 / 93
90.0% best2 / 83
85.0%3 / 83
100.0% best1 / 75
97.6%4 / 75
24.5 best1 / 59
21.22 / 59
22.5 best1 / 59
19.22 / 59
22.0% best2 / 55
17.0%4 / 55
65.8% best2 / 52
61.2%8 / 52
90.0% best1 / 40
89.2%2 / 40
50.2% best1 / 32
46.2%3 / 32
58.0%3 / 30
63.0% best1 / 30
69.9% best1 / 25
62.4%3 / 25
76.4%5 / 24
79.3% best1 / 24
43.9% best1 / 24
31.7%8 / 24
24.2%14 / 23
28.0% best8 / 23
59.6%7 / 23
63.6% best4 / 23