BenchAtlas

Rankings / Anthropic

Claude Opus 4 20250514

released 2025-05-14

BenchAtlas Index

as of 2026-07-14
44.0
base configuration
rank #259
8 families · 5 categories · high
35.6
base configuration
rank #317
7 families · 3 categories · medium

Benchmark evidence

87 results
external indices
ECI142.9 pointsindependentEpoch AI Benchmarking Hub
ECI2K budget142.9 pointsindependentEpoch AI Benchmarking Hub
ECI1K budget142.9 pointsindependentEpoch AI Benchmarking Hub
ECI8K budget142.9 pointsindependentEpoch AI Benchmarking Hub
ECI27K budget142.9 pointsindependentEpoch AI Benchmarking Hub
ECI16K budget142.9 pointsindependentEpoch AI Benchmarking Hub
ECI32K budget142.9 pointsindependentEpoch AI Benchmarking Hub
ECI12K budget142.9 pointsindependentEpoch AI Benchmarking Hub
human preference
Coding (style control)older version
arena=text · category=coding · style_control=true
1464.2
1456.9–1471.4
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1446.8
1439.6–1453.9
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1446.6
1434.5–1458.6
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1445.2
1433.1–1457.4
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1442.8
1436.0–1449.4
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1441.5
1435.6–1447.5
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1437.8
1426.7–1449.0
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1435.1
1422.5–1447.7
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1434.9
1429.5–1440.3
communityLMArena Leaderboard Dataset
German (style control)older version
arena=text · category=german · style_control=true
1430.5
1413.1–1447.9
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
1429.6
1421.9–1437.3
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1428.2
1420.6–1435.7
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1426.4
1415.3–1437.6
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1424.9
1419.6–1430.3
communityLMArena Leaderboard Dataset
French (style control)older version
arena=text · category=french · style_control=true
1422.3
1396.8–1447.8
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
1418.4
1411.5–1425.2
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1416.5
1408.0–1425.0
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1413.6
1407.2–1420.1
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1412.4
1408.1–1416.7
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1409.7
1398.3–1421.1
communityLMArena Leaderboard Dataset
Polish (style control)older version
arena=text · category=polish · style_control=true
1405.2
1393.7–1416.7
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1403.4
1392.3–1414.4
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
1402.4
1394.8–1410.0
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1399.6
1394.0–1405.3
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
1399.6
1392.3–1406.9
communityLMArena Leaderboard Dataset
Spanish (style control)older version
arena=text · category=spanish · style_control=true
1397.0
1376.2–1417.8
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1396.9
1391.6–1402.1
communityLMArena Leaderboard Dataset
Japanese (style control)older version
arena=text · category=japanese · style_control=true
1380.7
1360.9–1400.5
communityLMArena Leaderboard Dataset
Korean (style control)older version
arena=text · category=korean · style_control=true
1362.8
1342.8–1382.8
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond16K budget76.3 %independentEpoch AI Benchmarking Hub
2025-05-22
GPQA Diamond
implementation=vals-ai
71.7 %independentVals AI
GPQA Diamond69.2 %independentEpoch AI Benchmarking Hub
2025-05-22
MMLU-Pro
implementation=vals-ai
86.2 %independentVals AI
multimodal
MMMU
implementation=vals-ai
73.3 %independentVals AI
professional
LegalBench83.1 %independentVals AI
MedQA92.9 %independentVals AI
TaxEval71.9 %independentVals AI
reasoning math
AIME
implementation=vals-ai
41.3 %independentVals AI
ARC-AGI-1older version
split=public_eval · model_type=CoT
thinking · 16K budget54.3 %independentARC Prize Leaderboard
ARC-AGI-1older version
split=public_eval · model_type=CoT
thinking · 8K budget45.6 %independentARC Prize Leaderboard
ARC-AGI-1older version
split=public_eval · model_type=CoT
thinking · 1K budget43.3 %independentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
thinking · 16K budget35.7 %independentARC Prize Leaderboard
ARC-AGI-1older version
split=public_eval · model_type=CoT
35.5 %independentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
thinking · 8K budget30.7 %independentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
thinking · 1K budget27.0 %independentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
22.5 %independentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
thinking · 16K budget8.6 %independentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
thinking · 8K budget4.5 %independentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
thinking · 16K budget3.3 %independentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
thinking · 8K budget2.5 %independentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
thinking · 16K budget2.0 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
thinking · 16K budget1.9 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
1.3 %independentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
1.3 %independentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
thinking · 16K budget1.2 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
thinking · 8K budget1.2 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
thinking · 8K budget1.2 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-1older version
split=public_eval · model_type=CoT
thinking · 16K budget1.1 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-1older version
split=public_eval · model_type=CoT
thinking · 8K budget0.8 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
thinking · 1K budget0.8 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
thinking · 1K budget0.8 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
thinking · 8K budget0.7 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
0.7 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
0.6 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
thinking · 1K budget0.5 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=public_eval · model_type=CoT
thinking · 1K budget0.4 %independentARC Prize Leaderboard
ARC-AGI-1older version
split=public_eval · model_type=CoT
thinking · 1K budget0.4 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-1older version
split=semi_private · model_type=CoT
0.4 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-1older version
split=public_eval · model_type=CoT
0.3 usd_per_taskindependentARC Prize Leaderboard
ARC-AGI-2
split=semi_private · model_type=CoT
thinking · 1K budget0.0 %independentARC Prize Leaderboard
FrontierMath4.5 %independentEpoch AI Benchmarking Hub
2025-07-04
FrontierMath Tier 4older version27K budget4.2 %independentEpoch AI Benchmarking Hub
2025-07-01
FrontierMath27K budget4.1 %independentEpoch AI Benchmarking Hub
2025-08-05
FrontierMath Tier 4older version0.0 %independentEpoch AI Benchmarking Hub
2025-07-01
MATH-500
implementation=vals-ai
90.4 %independentVals AI
MATH Level 585.0 %independentEpoch AI Benchmarking Hub
2025-05-22
OTIS Mock AIME 2024–202527K budget64.4 %independentEpoch AI Benchmarking Hub
2025-05-28
OTIS Mock AIME 2024–202516K budget60.0 %independentEpoch AI Benchmarking Hub
2025-05-22
OTIS Mock AIME 2024–202542.2 %independentEpoch AI Benchmarking Hub
2025-05-22

Agent + model results

systems, not bare-model scores
agent + model Epoch Inspect harness + Claude Opus 4 20250514SWE-bench Verified70.7 %independentEpoch AI Benchmarking Hub

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

Related variants

Claude Opus 4.5 20251101Claude Opus 4.6Claude Opus 4.8Claude Opus 4.7Claude Opus 4.1 20250805Claude Opus 4.1Claude Opus 4Claude Opus 4.5