BenchAtlas

Rankings / DeepSeek

Deepseek LLM 67B Chat

released 2023-11-29

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

17 results
human preference
Coding (style control)older version
arena=text · category=coding · style_control=true
1217.1
1193.6–1240.6
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1205.8
1187.2–1224.3
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1204.9
1192.1–1217.6
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1189.4
1169.6–1209.3
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1183.8
1172.4–1195.3
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
1180.7
1159.0–1202.3
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1174.3
1155.9–1192.8
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
1169.3
1150.5–1188.0
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1156.1
1139.2–1173.0
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1155.5
1132.0–1179.0
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1151.0
1126.6–1175.3
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1148.7
1130.2–1167.2
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
1140.3
1119.0–1161.5
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1134.5
1112.7–1156.2
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1054.4
1037.6–1071.1
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond24.6 %independentEpoch AI Benchmarking Hub
2025-01-27
reasoning math
MATH Level 56.4 %independentEpoch AI Benchmarking Hub
2025-01-27