BenchAtlas

Rankings / DeepSeek

Deepseek R1

released 2025-01-20

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

34 results
external indices
ECI139.7 pointsindependentEpoch AI Benchmarking Hub
human preference
Coding (style control)older version
arena=text · category=coding · style_control=true
1444.6
1432.8–1456.4
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1433.5
1422.3–1444.7
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1430.5
1421.3–1439.7
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1428.6
1410.5–1446.7
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1418.5
1409.5–1427.5
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1414.1
1399.3–1428.9
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1412.8
1406.7–1418.9
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1412.0
1391.5–1432.5
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1411.5
1397.4–1425.5
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
1411.0
1400.7–1421.2
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1410.1
1398.2–1422.0
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1399.9
1380.1–1419.8
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1398.9
1381.2–1416.5
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1398.8
1386.8–1410.8
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1398.1
1393.3–1403.0
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1397.2
1389.7–1404.7
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
1388.1
1374.2–1402.0
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1383.3
1376.0–1390.5
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
1382.3
1374.1–1390.4
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1381.1
1368.2–1394.0
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1377.7
1370.8–1384.5
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1374.1
1363.8–1384.5
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
1372.4
1362.6–1382.3
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond69.2 %independentEpoch AI Benchmarking Hub
2025-05-26
MMLU-Pro
implementation=vals-ai
83.2 %independentVals AI
professional
CorpFin54.1 %independentVals AI
LegalBench67.3 %independentVals AI
MedQA90.8 %independentVals AI
TaxEval72.3 %independentVals AI
reasoning math
AIME
implementation=vals-ai
74.0 %independentVals AI
MATH-500
implementation=vals-ai
92.2 %independentVals AI
MATH Level 593.0 %independentEpoch AI Benchmarking Hub
2025-01-31
OTIS Mock AIME 2024–202553.3 %independentEpoch AI Benchmarking Hub
2025-02-26

Agent + model results

systems, not bare-model scores
agent + model terminus-1 + Deepseek R1Terminal-Bench 1.05.7 %communityTerminal-Bench Leaderboard

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

Related variants

Deepseek R1 0528