BenchAtlas

Rankings / ibm

Granite 4.1 8B

open weights

released 2026-04-29

BenchAtlas Index

as of 2026-07-14
17.8
base configuration
rank #421
7 families · 4 categories · medium

Benchmark evidence

25 results
agentic coding
τ²-Bench27.8 %independentArtificial Analysis
τ²-Bench
subset=banking
3.1 %independentArtificial Analysis
coding
SciCode21.8 %independentArtificial Analysis
external indices
AA Coding Index9.5 pointsindependentArtificial Analysis
Intelligence Index v4.16.7 pointsindependentArtificial Analysis
human preference
Coding (style control)older version
arena=text · category=coding · style_control=true
1351.5
1331.5–1371.5
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1349.2
1332.9–1365.5
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1340.4
1322.7–1358.0
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1331.5
1317.2–1345.7
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1322.6
1309.8–1335.4
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
1319.6
1294.4–1344.8
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1306.8
1296.7–1317.0
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
1299.3
1274.8–1323.7
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1295.3
1278.2–1312.3
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1289.4
1271.8–1307.0
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1286.9
1261.5–1312.2
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1277.5
1263.3–1291.6
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
1274.0
1252.7–1295.2
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1266.3
1240.8–1291.8
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
1258.2
1235.4–1281.1
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1254.9
1240.5–1269.2
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond
implementation=artificial-analysis
43.3 %independentArtificial Analysis
Humanity's Last Exam
implementation=artificial-analysis
3.8 %independentArtificial Analysis
long context instruction
AA-LCR12.0 %independentArtificial Analysis
IFBench38.6 %independentArtificial Analysis

Agent + model results

systems, not bare-model scores
agent + model Artificial Analysis harness + Granite 4.1 8BTerminal-Bench 2.13.4 %independentArtificial Analysis
agent + model Artificial Analysis harness + Granite 4.1 8BTerminal-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.