Rankings / MiniMax
Minimax M3
released 2026-06-01
BenchAtlas Index
as of 2026-07-14
base configuration
rank #106
7 families · 4 categories · medium
base configuration
rank #285
12 families · 5 categories · high
Benchmark evidence
49 results
agentic coding
| Release 2026-06-25 tasks_counted=3 · livebench_version=2026-06-25 | 40.7 % | independent | LiveBench | |
| τ²-Bench | 88.9 % | independent | Artificial Analysis | |
| τ²-Bench subset=banking | 13.0 % | independent | Artificial Analysis |
coding
| Release 2026-06-25 tasks_counted=2 · livebench_version=2026-06-25 | 68.2 % | independent | LiveBench | |
| SciCode | 45.4 % | independent | Artificial Analysis |
data analysis
| Release 2026-06-25 tasks_counted=3 · livebench_version=2026-06-25 | 76.2 % | independent | LiveBench |
external indices
| AA Coding Index | 58.6 points | independent | Artificial Analysis | |
| Intelligence Index v4.1 | 44.4 points | independent | Artificial Analysis | |
| ECI | 144.9 points | independent | Epoch AI Benchmarking Hub | |
| Vals Index | 58.9 points | independent | Vals AI |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1500.1 1491.9–1508.3 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1489.9 1482.6–1497.3 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1479.6 1467.2–1492.1 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1474.6 1455.4–1493.8 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1473.8 1465.8–1481.7 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1470.6 1455.2–1486.0 | 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 | 1467.2 1457.1–1477.3 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1465.8 1459.3–1472.3 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1459.1 1441.6–1476.5 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1457.9 1450.9–1464.9 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1454.6 1447.2–1462.0 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1453.3 1443.5–1463.2 | community | LMArena Leaderboard Dataset | |
| French (style control)older version arena=text · category=french · style_control=true | 1451.5 1430.2–1472.8 | 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 | 1449.4 1440.1–1458.7 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1445.1 1439.6–1450.6 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1444.4 1426.6–1462.1 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1443.2 1436.1–1450.4 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1438.7 1426.7–1450.8 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1438.3 1430.5–1446.1 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1429.3 1422.6–1435.9 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1428.9 1415.1–1442.8 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1428.4 1405.3–1451.6 | 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 | 1425.0 1416.3–1433.7 | 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 | 1409.5 1400.3–1418.6 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1406.3 1396.0–1416.6 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | 92.9 % | independent | Artificial Analysis | |
| GPQA Diamond implementation=vals-ai | 92.7 % | independent | Vals AI | |
| Humanity's Last Exam implementation=artificial-analysis | 37.1 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=vals-ai | 84.2 % | independent | Vals AI |
language
| Release 2026-06-25 tasks_counted=3 · livebench_version=2026-06-25 | 76.8 % | independent | LiveBench |
long context instruction
| AA-LCR | 74.0 % | independent | Artificial Analysis | |
| IFBench | 82.9 % | independent | Artificial Analysis | |
| Release 2026-06-25 tasks_counted=4 · livebench_version=2026-06-25 | 57.5 % | independent | LiveBench |
multimodal
| MMMU implementation=vals-ai | 81.2 % | independent | Vals AI |
professional
| CorpFin | 68.1 % | independent | Vals AI | |
| LegalBench | 85.4 % | independent | Vals AI | |
| TaxEval | 72.7 % | independent | Vals AI |
reasoning math
| Release 2026-06-25 tasks_counted=4 · livebench_version=2026-06-25 | 77.0 % | independent | LiveBench | |
| Release 2026-06-25 tasks_counted=4 · livebench_version=2026-06-25 | 74.5 % | independent | LiveBench |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Minimax M3 | Terminal-Bench 2.1 | 65.2 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + Minimax M3 | Terminal-Bench Hard | 42.4 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.