Rankings / Unknown
Intellect 3
open weightsreleased 2025-11-27
BenchAtlas Index
as of 2026-07-14
base configuration
rank #297
9 families · 5 categories · high
Benchmark evidence
27 results
agentic coding
| τ²-Bench | 26.6 % | independent | Artificial Analysis |
coding
| LiveCodeBench v6 implementation=artificial-analysis | 77.7 % | independent | Artificial Analysis | |
| SciCode | 39.1 % | independent | Artificial Analysis |
external indices
| Intelligence Index v4.1 | 15.6 points | independent | Artificial Analysis | |
| AA Math Index | 88.0 points | independent | Artificial Analysis |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1409.2 1390.4–1427.9 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1400.1 1385.9–1414.2 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1398.8 1383.4–1414.1 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1384.4 1373.0–1395.9 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1373.1 1361.7–1384.5 | 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 | 1367.4 1347.5–1387.3 | 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 | 1363.6 1345.0–1382.2 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1358.7 1338.3–1379.2 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1356.2 1347.9–1364.6 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1352.1 1335.1–1369.1 | 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 | 1336.4 1319.7–1353.1 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1329.5 1313.5–1345.4 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1323.5 1312.1–1335.0 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1317.5 1305.6–1329.4 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1311.4 1289.9–1332.9 | 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 | 1304.3 1285.5–1323.0 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | 76.1 % | independent | Artificial Analysis | |
| Humanity's Last Exam implementation=artificial-analysis | 12.1 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=artificial-analysis | 82.2 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | 32.3 % | independent | Artificial Analysis | |
| IFBench | 34.0 % | independent | Artificial Analysis |
reasoning math
| AIME year=2025 · implementation=artificial-analysis | 88.0 % | independent | Artificial Analysis |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Intellect 3 | Terminal-Bench Hard | 9.1 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.