BenchAtlas

Rankings / allenai

Olmo 3.1 32B Instruct

open weights

released 2026-01-13

BenchAtlas Index

as of 2026-07-14
18.5
base configuration
rank #418
7 families · 4 categories · medium

Benchmark evidence

29 results
agentic coding
τ²-Bench21.4 %independentArtificial Analysis
coding
SciCode16.7 %independentArtificial Analysis
external indices
Intelligence Index v4.16.5 pointsindependentArtificial Analysis
human preference
Coding (style control)older version
arena=text · category=coding · style_control=true
1384.0
1372.2–1395.9
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1378.3
1369.0–1387.7
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1373.4
1362.5–1384.3
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1366.2
1357.9–1374.6
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1355.3
1335.3–1375.2
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1349.7
1341.8–1357.6
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
1348.3
1335.7–1360.9
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
1342.3
1328.0–1356.7
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1336.9
1325.9–1348.0
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1331.6
1309.4–1353.8
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1330.2
1324.1–1336.3
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1328.8
1315.7–1341.8
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1324.7
1298.2–1351.3
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1322.2
1311.5–1332.8
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1321.8
1298.8–1344.7
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1305.4
1282.6–1328.2
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
1301.9
1290.0–1313.8
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1299.3
1283.2–1315.5
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
1296.0
1282.8–1309.2
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1292.2
1284.4–1300.1
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1291.7
1276.8–1306.5
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1277.3
1268.2–1286.4
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond
implementation=artificial-analysis
53.9 %independentArtificial Analysis
Humanity's Last Exam
implementation=artificial-analysis
4.9 %independentArtificial Analysis
long context instruction
AA-LCR0.0 %independentArtificial Analysis
IFBench39.2 %independentArtificial Analysis

Agent + model results

systems, not bare-model scores
agent + model Artificial Analysis harness + Olmo 3.1 32B InstructTerminal-Bench Hard0.0 %independentArtificial Analysis

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