BenchAtlas

Rankings / Anthropic

Claude Fable 5

released 2026-06-09

BenchAtlas Index

as of 2026-07-14
82.7
max effort
rank #5
6 families · 3 categories · medium
65.0
xhigh effort
rank #95
5 families · 4 categories · medium
61.8
max effort
rank #126
6 families · 4 categories · medium

Benchmark evidence

47 results
agentic coding
Release 2026-06-25
tasks_counted=3 · livebench_version=2026-06-25
xhigh effort50.7 %independentLiveBench
Release 2026-06-25
tasks_counted=3 · livebench_version=2026-06-25
max effort46.9 %independentLiveBench
coding
Release 2026-06-25
tasks_counted=2 · livebench_version=2026-06-25
max effort86.0 %independentLiveBench
Release 2026-06-25
tasks_counted=2 · livebench_version=2026-06-25
xhigh effort82.5 %independentLiveBench
data analysis
Release 2026-06-25
tasks_counted=3 · livebench_version=2026-06-25
max effort80.5 %independentLiveBench
Release 2026-06-25
tasks_counted=3 · livebench_version=2026-06-25
xhigh effort78.7 %independentLiveBench
external indices
ECIxhigh effort160.4 pointsindependentEpoch AI Benchmarking Hub
ECI160.4 pointsindependentEpoch AI Benchmarking Hub
ECImax effort160.4 pointsindependentEpoch AI Benchmarking Hub
ECIhigh effort160.4 pointsindependentEpoch AI Benchmarking Hub
Vals Indexmax effort75.1 pointsindependentVals AI
factuality
SimpleQA Verifiedxhigh effort68.3 %independentEpoch AI Benchmarking Hub
2026-06-09
human preference
Expert (style control)older version
arena=text · category=expert · style_control=true
1551.4
1530.9–1571.9
communityLMArena Leaderboard Dataset
Coding (style control)older version
arena=text · category=coding · style_control=true
1548.3
1535.1–1561.5
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1534.9
1523.9–1545.9
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1534.4
1525.6–1543.3
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1533.0
1520.7–1545.4
communityLMArena Leaderboard Dataset
Industry Life And Physical And Social Science (style control)older version
arena=text · category=industry_life_and_physical_and_social_science · style_control=true
1529.7
1513.0–1546.5
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1527.3
1517.5–1537.1
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1524.8
1513.9–1535.6
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1523.6
1497.6–1549.6
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1519.6
1497.6–1541.6
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1514.1
1502.3–1525.9
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1513.6
1496.7–1530.6
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1513.5
1503.3–1523.8
communityLMArena Leaderboard Dataset
Industry Writing And Literature And Language (style control)older version
arena=text · category=industry_writing_and_literature_and_language · style_control=true
1510.0
1496.3–1523.8
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1509.1
1492.7–1525.4
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1507.5
1500.0–1515.0
communityLMArena Leaderboard Dataset
Industry Entertainment And Sports And Media (style control)older version
arena=text · category=industry_entertainment_and_sports_and_media · style_control=true
1496.5
1482.3–1510.7
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1495.7
1486.2–1505.1
communityLMArena Leaderboard Dataset
Industry Business And Management And Financial Operations (style control)older version
arena=text · category=industry_business_and_management_and_financial_operations · style_control=true
1493.8
1479.0–1508.7
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1492.5
1467.7–1517.2
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond
implementation=vals-ai
max effort93.2 %independentVals AI
MMLU-Pro
implementation=vals-ai
max effort91.5 %independentVals AI
language
Release 2026-06-25
tasks_counted=3 · livebench_version=2026-06-25
max effort90.7 %independentLiveBench
Release 2026-06-25
tasks_counted=3 · livebench_version=2026-06-25
xhigh effort89.5 %independentLiveBench
long context instruction
Release 2026-06-25
tasks_counted=4 · livebench_version=2026-06-25
max effort75.8 %independentLiveBench
Release 2026-06-25
tasks_counted=4 · livebench_version=2026-06-25
xhigh effort72.0 %independentLiveBench
multimodal
MMMU
implementation=vals-ai
max effort89.3 %independentVals AI
professional
CorpFinmax effort71.8 %independentVals AI
LegalBenchmax effort88.6 %independentVals AI
TaxEvalmax effort76.9 %independentVals AI
reasoning math
Release 2026-06-25
tasks_counted=4 · livebench_version=2026-06-25
max effort96.0 %independentLiveBench
Release 2026-06-25
tasks_counted=4 · livebench_version=2026-06-25
xhigh effort95.7 %independentLiveBench
Release 2026-06-25
tasks_counted=4 · livebench_version=2026-06-25
max effort89.7 %independentLiveBench
Release 2026-06-25
tasks_counted=4 · livebench_version=2026-06-25
xhigh effort87.7 %independentLiveBench
OTIS Mock AIME 2024–2025max effort99.7 %independentEpoch AI Benchmarking Hub
2026-06-10

Agent + model results

systems, not bare-model scores
agent + model Claude Code + Claude Fable 5Terminal-Bench 2.183.2 %communityTerminal-Bench Leaderboard
agent + model terminus-2 + Claude Fable 5Terminal-Bench 2.180.5 %communityTerminal-Bench Leaderboard

These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.