Inference
EN

Claude Fable 5.1 vs Gemini 4 Argon

Change models
Claude Fable 5.1Anthropic
Gemini 4 ArgonGoogle
IndexAll categories, out of 100.
76.2 ±2.4
78.5 ±4.3 best
GapIndex points below the top.
−2.3 · no clear gap
Top
CoverageIndex weight that has results.
95% best
80%
SpeedOutput tokens per second.
69/s best
28/s
EloLMArena rating and rank.
1512
1530 best
ReleasedMonth of release.
2026-09
2026-09
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
77.3 best
CodingCode writing and repair.
77.7 best
76.7
ReasoningLogic problems and puzzles.
75.8
79.8 best
MultimodalTasks with images and text.
77.9
—
KnowledgeFacts and expert knowledge.
77.2 best
76.5
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
74.3
—
MathMath problems.
77.0 best
75.9

Benchmarks

68 shared
Only Claude Fable 5.1: 64Only Gemini 4 Argon: 18
Claude Fable 5.1
Gemini 4 Argon
Artificial Analysis Humanity's Last ExamKnowledge
59.1% best3 / 222
57.1%4 / 222
Artificial Analysis Long Context ReasoningReasoning
85.3% best5 / 217
79.7%45 / 217
Critical Physics TasksReasoning
29.7% best12 / 214
27.1%17 / 214
OTIS Mock AIME 2024-2025Math
100.0%1 / 200
100.0%1 / 200
Artificial Analysis Omniscience AccuracyKnowledge
68.4% best2 / 164
48.3%26 / 164
LegalBenchLegal
88.5% best2 / 149
88.3%3 / 149
GDPval-AA normalizedAgentic
62.7% best6 / 133
56.2%14 / 133
ARC-AGI-2 (semi-private)Reasoning
90.0%9 / 131
91.3% best7 / 131
ARC-AGI-1 (semi-private)Reasoning
97.5%5 / 126
98.5% best1 / 126
Vibe Code Bench v1.1Coding
90.3%6 / 123
91.9% best3 / 123
ARC-AGI-2 (public eval)Reasoning
98.3% best2 / 122
97.1%6 / 122
ARC-AGI-1 (public eval)Reasoning
99.0%2 / 116
99.5% best1 / 116
Artificial Analysis SciCodeCoding
63.1% best3 / 114
61.8%5 / 114
MedScribeHealthcare
91.3% best2 / 109
87.4%17 / 109
MedCodeHealthcare
53.5%8 / 106
58.8% best3 / 106
SimpleQA VerifiedKnowledge
70.8%8 / 91
76.0% best3 / 91
Chess PuzzlesReasoning
48.0%19 / 90
59.0% best10 / 90
FrontierMath-Tiers-1-3-v2-PrivateMath
90.2% best7 / 90
86.0%13 / 90
Legal Research BenchLegal
55.3% best2 / 90
54.8%5 / 90
Tax Agent BenchFinance
50.7% best2 / 82
49.2%4 / 82