BenchAtlas

Rankings / Unknown

Trinity Large Thinking

open weights

released 2026-04-01

BenchAtlas Index

as of 2026-09-11
40.1
base configuration
rank #307
7 families · 4 categories · medium

Benchmark evidence

36 results
agentic coding
τ²-Bench90.1 %independentArtificial Analysis
τ²-Bench
subset=banking
5.8 %independentArtificial Analysis
coding
SciCode40.6 %independentArtificial Analysis
external indices
AA Coding Index25.8 pointsindependentArtificial Analysis
Intelligence Index v4.110.9 pointsindependentArtificial Analysis
human preference
Coding (style control)older version
arena=text · category=coding · style_control=true
1414.2
1406.6–1421.7
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1407.2
1400.7–1413.7
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1401.3
1389.1–1413.5
communityLMArena Leaderboard Dataset
French (style control)older version
arena=text · category=french · style_control=true
1398.9
1377.9–1419.8
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1397.1
1381.8–1412.3
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1397.0
1383.1–1410.9
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1396.2
1389.1–1403.2
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
1393.3
1384.0–1402.6
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1385.9
1380.3–1391.5
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1385.5
1370.3–1400.7
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1383.7
1377.6–1389.7
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1378.5
1362.8–1394.2
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1376.8
1363.5–1390.0
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
1369.5
1360.9–1378.1
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1369.1
1364.4–1373.8
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1366.5
1359.7–1373.2
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1358.5
1347.1–1369.9
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1358.2
1351.2–1365.1
communityLMArena Leaderboard Dataset
Spanish (style control)older version
arena=text · category=spanish · style_control=true
1355.9
1334.7–1377.2
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1353.4
1347.5–1359.2
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1348.2
1339.2–1357.3
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1346.7
1340.4–1353.0
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
1344.6
1336.7–1352.5
communityLMArena Leaderboard Dataset
Polish (style control)older version
arena=text · category=polish · style_control=true
1344.3
1318.2–1370.4
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1333.9
1324.3–1343.5
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
1327.2
1318.6–1335.9
communityLMArena Leaderboard Dataset
Korean (style control)older version
arena=text · category=korean · style_control=true
1325.4
1298.7–1352.1
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond
implementation=artificial-analysis
75.2 %independentArtificial Analysis
Humanity's Last Exam
implementation=artificial-analysis
15.8 %independentArtificial Analysis
long context instruction
AA-LCR38.0 %independentArtificial Analysis
IFBench56.3 %independentArtificial Analysis

Agent + model results

systems, not bare-model scores
agent + model Artificial Analysis harness + Trinity Large ThinkingTerminal-Bench Hard22.7 %independentArtificial Analysis
agent + model Artificial Analysis harness + Trinity Large ThinkingTerminal-Bench 2.120.6 %independentArtificial Analysis

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