BenchAtlas

Rankings / OpenAI

GPT 4.5 Preview (2025-02-27)

released 2025-02-27

BenchAtlas Index

as of 2026-07-14
Not enough benchmark coverage for a composite score (needs ≥4 families across ≥3 categories). The per-benchmark evidence below stands on its own — sparse coverage is an evidence gap, not a low score.

Benchmark evidence

30 results
external indices
Intelligence Index v4.113.6 pointsindependentArtificial Analysis
ECI137.5 pointsindependentEpoch AI Benchmarking Hub
factuality
MASK56.9 %
52.961.0
independentScale Labs
human preference
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1468.6
1446.01491.1
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1466.3
1452.91479.7
communityLMArena Leaderboard Dataset
Coding (style control)older version
arena=text · category=coding · style_control=true
1459.1
1446.01472.1
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1459.0
1448.81469.2
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1456.2
1436.51475.9
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1452.4
1443.81461.0
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1450.0
1425.51474.4
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
1448.9
1437.11460.7
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1447.6
1440.51454.7
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
1447.0
1437.31456.6
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1446.6
1431.11462.1
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1444.7
1439.01450.4
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1444.3
1432.11456.6
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1443.0
1429.31456.6
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1440.5
1430.51450.5
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1438.2
1430.21446.2
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1437.2
1428.91445.5
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1436.2
1424.31448.2
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
1435.7
1424.01447.4
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1428.7
1405.21452.2
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
1425.7
1410.21441.3
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1413.4
1397.81429.0
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1408.8
1393.51424.0
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond68.7 %independentEpoch AI Benchmarking Hub
2025-02-28
Humanity's Last Exam
contamination=Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. · implementation=scale
5.4 %
4.56.3
independentScale Labs
reasoning math
MATH Level 578.6 %independentEpoch AI Benchmarking Hub
2025-02-28
OTIS Mock AIME 2024–202537.8 %independentEpoch AI Benchmarking Hub
2025-02-28