Inference
EN

Claude Fable 5.1 vs Gemini 4 Hydrogen

Change models
Claude Fable 5.1Anthropic
Gemini 4 HydrogenGoogle
IndexAll categories, out of 100.
75.7 ±2.4
76.9 ±8.4 best
GapIndex points below the top.
−1.2 · no clear gap
Top
CoverageIndex weight that has results.
95% best
65%
SpeedOutput tokens per second.
69/s
—
EloLMArena rating and rank.
1512
—
ReleasedMonth of release.
2026-09
2026-11
Input / 1MUS dollars per 1M input tokens.
$10.00
$1.50 best
Output / 1MUS dollars per 1M output tokens.
$50.00
$7.50 best
Batch output / 1MBatch price per 1M output tokens.
$25.00
—
1K chats2K tokens in, 500 out, each.
$45.00
$6.75 best
1K documents20K tokens in, 1K out, each.
$250.00
$37.50 best
1K agent tasks200K tokens in, 20K out, each.
$3,000.00
$450.00 best
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
71.0
78.5 best
CodingCode writing and repair.
77.5
79.1 best
ReasoningLogic problems and puzzles.
75.6
—
MultimodalTasks with images and text.
74.5
80.5 best
KnowledgeFacts and expert knowledge.
77.0 best
74.3
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
74.1
—
MathMath problems.
76.8
—

Benchmarks

9 shared
Only Claude Fable 5.1: 124Only Gemini 4 Hydrogen: 2
Claude Fable 5.1
Gemini 4 Hydrogen
Artificial Analysis Omniscience AccuracyKnowledge
68.4% best2 / 165
50.5%19 / 165
FrontierCode 2.0Coding
32.4%9 / 28
38.2% best7 / 28
Artificial Analysis AutomationBenchAgentic
59.4%14 / 23
76.1% best4 / 23
Artificial Analysis GDP.pdfAgentic
26.2%9 / 22
27.6% best8 / 22
Artificial Analysis Terminal-Bench v4.0Agentic
52.0%11 / 22
53.5% best10 / 22
cursorBench40Coding
51.8%7 / 21
54.3% best5 / 21
Terminal-Bench-Science 0.1Agentic
52.6% best8 / 12
51.4%9 / 12
OSWorld 2.1 offline subset (82 tasks)Agentic
83.5% best4 / 11
77.6%6 / 11
Chartography without toolsMultimodal
42.6%8 / 10
66.6% best4 / 10