Rankings / ibm
Granite 4.1 8B
open weightsreleased 2026-04-29
BenchAtlas Index
as of 2026-09-11
base configuration
rank #444
7 families · 4 categories · medium
Benchmark evidence
25 results
agentic coding
| τ²-Bench | 27.8 % | independent | Artificial Analysis | |
| τ²-Bench subset=banking | 3.1 % | independent | Artificial Analysis |
coding
| SciCode | 21.8 % | independent | Artificial Analysis |
external indices
| AA Coding Index | 9.5 points | independent | Artificial Analysis | |
| Intelligence Index v4.1 | 6.6 points | independent | Artificial Analysis |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1353.6 1333.6–1373.6 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1351.1 1334.8–1367.4 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1338.7 1320.9–1356.5 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1331.0 1316.7–1345.4 | 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 | 1323.3 1298.2–1348.4 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1321.2 1308.3–1334.0 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1306.0 1295.8–1316.2 | 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 | 1301.2 1276.9–1325.5 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1293.9 1276.8–1311.0 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1287.3 1269.7–1305.0 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1284.2 1258.8–1309.6 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1275.9 1261.7–1290.0 | 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 | 1275.9 1254.7–1297.1 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1268.1 1242.6–1293.5 | 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 | 1261.1 1238.3–1283.9 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1253.8 1239.4–1268.2 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | 43.3 % | independent | Artificial Analysis | |
| Humanity's Last Exam implementation=artificial-analysis | 3.8 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | 13.3 % | independent | Artificial Analysis | |
| IFBench | 38.6 % | independent | Artificial Analysis |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Granite 4.1 8B | Terminal-Bench 2.1 | 3.4 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + Granite 4.1 8B | Terminal-Bench Hard | 0.0 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.