Inference
EN

Claude Fable 5.1 vs Gemini 4 Carbon

Change models
Claude Fable 5.1Anthropic
Gemini 4 CarbonGoogle
IndexAll categories, out of 100.
76.2 ±2.4
82.7 ±5.1 best
GapIndex points below the top.
−6.5
Top
CoverageIndex weight that has results.
95% best
80%
SpeedOutput tokens per second.
69/s best
31/s
EloLMArena rating and rank.
1512
1538 best
ReleasedMonth of release.
2026-09
2026-10
Input / 1MUS dollars per 1M input tokens.
$10.00
$2.00 best
Output / 1MUS dollars per 1M output tokens.
$50.00
$10.00 best
Batch output / 1MBatch price per 1M output tokens.
$25.00
$5.00 best
1K chats2K tokens in, 500 out, each.
$45.00
$9.00 best
1K documents20K tokens in, 1K out, each.
$250.00
$50.00 best
1K agent tasks200K tokens in, 20K out, each.
$3,000.00
$600.00 best
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
71.1
83.2 best
CodingCode writing and repair.
77.7
80.5 best
ReasoningLogic problems and puzzles.
75.8
83.9 best
MultimodalTasks with images and text.
77.9
—
KnowledgeFacts and expert knowledge.
77.2
79.5 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
74.3
—
MathMath problems.
77.0
77.2 best

Benchmarks

33 shared
Only Claude Fable 5.1: 99Only Gemini 4 Carbon: 6
Claude Fable 5.1
Gemini 4 Carbon
Artificial Analysis Long Context ReasoningReasoning
85.3% best5 / 217
79.3%52 / 217
OTIS Mock AIME 2024-2025Math
100.0%1 / 200
100.0%1 / 200
Artificial Analysis Omniscience AccuracyKnowledge
68.4% best2 / 164
58.3%9 / 164
ARC-AGI-2 (semi-private)Reasoning
90.0%9 / 131
92.1% best5 / 131
ARC-AGI-1 (semi-private)Reasoning
97.5%5 / 126
97.5%5 / 126
Vibe Code Bench v1.1Coding
90.3% best6 / 123
89.1%9 / 123
ARC-AGI-2 (public eval)Reasoning
98.3% best2 / 122
97.9%3 / 122
ARC-AGI-1 (public eval)Reasoning
99.0% best2 / 116
98.5%6 / 116
SimpleQA VerifiedKnowledge
70.8%8 / 91
77.7% best2 / 91
Chess PuzzlesReasoning
48.0%19 / 90
78.0% best2 / 90
FrontierMath-Tiers-1-3-v2-PrivateMath
90.2%7 / 90
90.5% best6 / 90
Legal Research BenchLegal
55.3%2 / 90
55.8% best1 / 90
Tax Agent BenchFinance
50.7%2 / 82
51.8% best1 / 82
Mystery Game PuzzlesReasoning
58.0%10 / 80
73.0% best5 / 80
FrontierMath-Tier-4-v2-PrivateMath
87.8%9 / 72
95.1% best4 / 72
Terminal-Bench 4.0Agentic
58.1%6 / 61
63.1% best4 / 61
Agent Arena steerabilityAgentic
14.85 / 54
19.1 best2 / 54
Agent Arena task outcomeAgentic
14.45 / 54
18.4 best4 / 54
Furniture AssemblyReasoning
70.0%9 / 37
77.5% best6 / 37
AutomationBenchAgentic
31.4%26 / 32
53.9% best5 / 32