BenchAtlas

Rankings / OpenAI

GPT 4 0125 Preview

released 2024-01-25

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
human preference
French (style control)older version
arena=text · category=french · style_control=true
1337.4
1315.3–1359.4
communityLMArena Leaderboard Dataset
Coding (style control)older version
arena=text · category=coding · style_control=true
1331.4
1323.8–1339.0
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1325.6
1313.9–1337.3
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1324.2
1319.2–1329.3
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1320.2
1313.8–1326.6
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1318.9
1311.7–1326.2
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
1316.5
1308.7–1324.2
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1312.7
1308.6–1316.8
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1311.9
1300.0–1323.8
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1311.5
1301.7–1321.2
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1306.7
1298.1–1315.3
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1306.3
1300.1–1312.5
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
1304.6
1297.9–1311.3
communityLMArena Leaderboard Dataset
Spanish (style control)older version
arena=text · category=spanish · style_control=true
1301.0
1278.5–1323.4
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1299.3
1291.5–1307.2
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1298.7
1290.6–1306.9
communityLMArena Leaderboard Dataset
German (style control)older version
arena=text · category=german · style_control=true
1294.2
1279.3–1309.0
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1293.5
1288.0–1299.0
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1292.4
1283.5–1301.4
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1291.1
1283.3–1299.0
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1289.5
1283.8–1295.3
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
1287.3
1279.4–1295.2
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
1283.5
1274.6–1292.4
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1280.0
1271.8–1288.2
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1277.9
1265.9–1289.9
communityLMArena Leaderboard Dataset
Japanese (style control)older version
arena=text · category=japanese · style_control=true
1251.7
1233.4–1269.9
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1244.3
1238.0–1250.5
communityLMArena Leaderboard Dataset
Korean (style control)older version
arena=text · category=korean · style_control=true
1244.2
1223.4–1265.0
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond42.3 %independentEpoch AI Benchmarking Hub
2025-01-27
reasoning math
MATH Level 535.4 %independentEpoch AI Benchmarking Hub
2025-01-27

Agent + model results

systems, not bare-model scores
agent + model AutoCodeRover (v20240408) + GPT 4 0125 PreviewSWE-bench Lite19.0 %unverifiedSWE-bench Leaderboard

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