Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Claude Fable 5

Anthropic

Strongest in Core abilities (#1 of 204, on 2 of its 3 boards), weakest in Reasoning (#13 of 140). Above par in 24 of 24 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 5.5 and ahead of Claude Opus 5 and Claude Fable 5.1.

§ 1 · Profile

What it is good at

Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.

Core abilities67.4#1/204
Language71.5#1/57
General intelligence69.9#2/204
Data analysis61.9#4/57
Instruction following63.9#6/57
Professional61.6#1/168
Medical63.5#2/140
Legal62.7#4/151
Finance61.5#4/151
Agents67.2#3/268
Computer use71.7#1/37
Web research64.2#1/4
Knowledge work67.7#11/178
Human preference67#3/342
Human preference67#3/342
Coding65.4#3/165
Code generation67.6#3/77
Agentic coding64.8#4/157
Knowledge60.7#4/138
Academic knowledge62.8#3/123
Reasoning62.9#5/178
Mathematics63.8#5/140
Science61.9#11/122
Reasoning62.3#13/140

§ 2 · Head to head

What it beats, and what beats it

The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for Claude Fable 5, left for the other.

GPT OSS 20Bwon 15 · lost 0
GPT-4owon 15 · lost 0
GPT-5 Nanowon 15 · lost 0
MiniMax M2.7won 15 · lost 0
Qwen3 Maxwon 15 · lost 0
Grok 4.1 Fastwon 15 · lost 0
Mimo V2.5won 15 · lost 0
Gemma 4 31Bwon 15 · lost 0
Muse Sparkwon 15 · lost 0
Qwen3.6 27Bwon 16 · lost 0
Llama 4 Scout Instructwon 16 · lost 0
Command Awon 16 · lost 0
Gemini 2.0 Flashwon 16 · lost 0
Grok 3 Miniwon 16 · lost 0
Claude 3.7 Sonnetwon 16 · lost 0
MiniMax M2.5won 16 · lost 0
Grok 4 Fastwon 16 · lost 0
Inkling Smallwon 16 · lost 0
GLM-4.7won 16 · lost 0
GLM-5won 16 · lost 0
GLM-5.1won 16 · lost 0
Nemotron 3 Ultrawon 17 · lost 0
O3 Miniwon 17 · lost 0
Grok 4won 17 · lost 0
GPT-4.1won 17 · lost 0
Kimi K2won 17 · lost 0
Qwen3 235B A22B Instructwon 17 · lost 0
GLM-4.6won 17 · lost 0
Mistral Medium 3.5won 17 · lost 0
Claude Opus 4won 17 · lost 0
Gemini 3.1 Flash Litewon 17 · lost 0
Mimo V2.5 Prowon 17 · lost 0
Gemini 3 Prowon 17 · lost 0
GPT-4o Miniwon 18 · lost 0
GPT-4.1 Nanowon 18 · lost 0
GPT OSS 120Bwon 18 · lost 0
GPT-4.1 Miniwon 18 · lost 0
GPT-5 Miniwon 18 · lost 0
O4 Miniwon 18 · lost 0
Gemini 2.5 Flashwon 18 · lost 0
Mistral Large 3won 18 · lost 0
Claude Haiku 4.5won 18 · lost 0
DeepSeek R1won 18 · lost 0
DeepSeek V3.2won 18 · lost 0
GPT-5won 18 · lost 0
DeepSeek V3won 19 · lost 0
O3won 19 · lost 0
GPT-6 Lunawon 19 · lost 0
Gemini 2.5 Prowon 19 · lost 0
Kimi K2.5won 19 · lost 0
Claude Sonnet 4.5won 19 · lost 0
Claude Sonnet 4won 20 · lost 0
GPT-5.2won 21 · lost 0
GPT-5.4 Miniwon 21 · lost 0
Claude Opus 4.5won 21 · lost 0
DeepSeek V4.1 Flashwon 21 · lost 0
GPT-5.4 Nanowon 22 · lost 0
Qwen3.8 27Bwon 22 · lost 0
DeepSeek V4 Flashwon 22 · lost 0
Grok 4.3won 22 · lost 0
Qwen3.6 Pluswon 22 · lost 0
Gemini 3.5 Flash Litewon 22 · lost 0
DeepSeek V4 Prowon 22 · lost 0
GPT-5.6 Terrawon 22 · lost 0
GLM-5.3 Flashwon 22 · lost 0
Qwen3.7 Maxwon 22 · lost 0
GPT-5.4won 22 · lost 0
GLM-5.2won 22 · lost 0
Claude Opus 4.8won 22 · lost 0
Kimi K3won 22 · lost 0
Claude Opus 4.7won 22 · lost 0
Inklingwon 23 · lost 0
GPT-5.6 Lunawon 23 · lost 0
Kimi K2.6won 23 · lost 0
Claude Sonnet 5won 23 · lost 0
Grok 4.5won 23 · lost 0
Claude Sonnet 4.6won 23 · lost 0
Gemini 3.5 Flashwon 23 · lost 0
MiniMax M3won 24 · lost 0
Muse Spark 1.1won 22 · lost 1
GLM-5.3won 21 · lost 1
Gemini 3.6 Flashwon 21 · lost 1
Muse Spark 1.2won 20 · lost 1
Grok 4.7won 18 · lost 1
GPT-6 Solwon 18 · lost 1
GPT-5.1won 15 · lost 1
GPT-5.6 Solwon 21 · lost 2
Qwen3.8 Maxwon 20 · lost 2
Gemini 3.1 Prowon 20 · lost 2
Gemini 3.7 Flashwon 20 · lost 2
Claude Opus 4.6won 18 · lost 2
GPT-5.5won 19 · lost 3
Gemini 3.8 Flashwon 19 · lost 3
Grok 4.6won 18 · lost 4
GPT-6 Astrawon 15 · lost 4
Muse Spark 1.3won 14 · lost 4
Claude Fable 5.1won 12 · lost 10
Claude Opus 5won 12 · lost 11
Claude Opus 5.5won 8 · lost 11

§ 3 · Sources

Where the numbers come from

9 publications, 31 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-09-26
LMArena Text 1504
GDPval-AA ↗1 measureread 2026-09-26
GDPval-AA 1595
AA-Briefcase ↗1 measureread 2026-09-26
AA-Briefcase 1541
Terminal-Bench ↗1 measureread 2026-09-26
Terminal-Bench 44.5% (Claude Code)
ARC-AGI-2 ↗1 measureread 2026-09-26
ARC-AGI-2 89.2%
LiveBench ↗8 measuresread 2026-09-26
LiveBench 83LiveBench · Reasoning 89.7LiveBench · Coding 86LiveBench · Agentic Coding 62.2LiveBench · Mathematics 96LiveBench · Data Analysis 80.5LiveBench · Language 90.7LiveBench · Instruction Following 75.8
OSWorld ↗1 measureread 2026-09-26
OSWorld 86%
Kagi LLM Benchmark ↗1 measureread 2026-09-26
Kagi LLM Benchmark 91.4%
Vals.ai ↗16 measuresread 2026-09-26
Vals · Legal Research Bench 49.52%Vals · LegalBench 88.56%Vals · Harvey Legal Agent Benchmark 11.25%Vals · Finance Agent 56.31%Vals · CorpFin 71.83%Vals · TaxEval 76.94%Vals · MortgageTax 68.92%Vals · MedCode 56.07%Vals · MedScribe 88.52%Vals · Web Search Index 48.45% (Exa)Vals · SWE-bench Verified 95% (Mini-SWE-agent)Vals · Vibe Code Bench 90.35% (OpenHands)Vals · Code Migration 55.06%Vals · GPQA Diamond 93.18%Vals · MMLU Pro 91.5%Vals · ProofBench 95%

Badge

PublicAI Index badge for Claude Fable 5[![PublicAI Index](https://publicai.io/model-index/badge?model=claude-fable-5)](https://publicai.io/model-index/m/claude-fable-5)