Rankings / allenai
Olmo 3 32B Think
open weightsreleased 2025-11-20
BenchAtlas Index
as of 2026-09-11
base configuration
rank #409
9 families · 5 categories · high
Benchmark evidence
28 results
agentic coding
| τ²-Bench | 0.0 % | independent | Artificial Analysis |
coding
| LiveCodeBench v6 implementation=artificial-analysis | 67.2 % | independent | Artificial Analysis | |
| SciCode | 28.6 % | independent | Artificial Analysis |
external indices
| Intelligence Index v4.1 | 6.5 points | independent | Artificial Analysis | |
| AA Math Index | 73.7 points | independent | Artificial Analysis |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1363.7 1345.0–1382.4 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1359.6 1345.6–1373.6 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1356.0 1339.3–1372.6 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1351.4 1339.3–1363.4 | community | LMArena 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 | 1327.9 1308.1–1347.8 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1326.5 1315.2–1337.7 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1320.9 1304.3–1337.5 | community | LMArena 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 | 1310.2 1291.9–1328.6 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1306.7 1298.4–1315.0 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1300.7 1278.5–1322.8 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1299.7 1283.8–1315.7 | community | LMArena Leaderboard Dataset | |
| Industry Writing And Literature And Language (style control)older version arena=text · category=industry_writing_and_literature_and_language · style_control=true | 1277.9 1261.2–1294.7 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1272.3 1247.1–1297.5 | community | LMArena Leaderboard Dataset | |
| Industry Entertainment And Sports And Media (style control)older version arena=text · category=industry_entertainment_and_sports_and_media · style_control=true | 1267.9 1249.4–1286.3 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1265.0 1254.0–1276.0 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1264.2 1243.4–1285.1 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1248.9 1236.6–1261.2 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | 61.0 % | independent | Artificial Analysis | |
| Humanity's Last Exam implementation=artificial-analysis | 6.4 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=artificial-analysis | 75.9 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | 0.0 % | independent | Artificial Analysis | |
| IFBench | 49.1 % | independent | Artificial Analysis |
reasoning math
| AIME year=2025 · implementation=artificial-analysis | 73.7 % | independent | Artificial Analysis |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Olmo 3 32B Think | Terminal-Bench Hard | 1.5 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.