Rankings / MiniMax
Minimax M2 7
released 2026-03-18
BenchAtlas Index
as of 2026-09-11
base configuration
rank #158
7 families · 4 categories · medium
base configuration
rank #235
7 families · 3 categories · medium
Benchmark evidence
48 results
agentic coding
| τ²-Bench | 84.8 % | independent | Artificial Analysis | |
| τ²-Bench subset=banking | 9.9 % | independent | Artificial Analysis |
coding
| SciCode | 50.1 % | independent | Artificial Analysis |
external indices
| AA Coding Index | 52.6 points | independent | Artificial Analysis | |
| Intelligence Index v4.1 | 23.2 points | independent | Artificial Analysis | |
| ECI | 145.7 points | independent | Epoch AI Benchmarking Hub | |
| Vals Index | 24.6 points | independent | Vals AI |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1480.2 1474.6–1485.8 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1468.8 1463.9–1473.8 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1457.7 1452.1–1463.3 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1450.3 1441.9–1458.6 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1442.4 1431.8–1453.0 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1440.4 1436.0–1444.7 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1435.4 1424.3–1446.4 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1435.3 1430.4–1440.1 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1431.7 1426.6–1436.8 | 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 | 1430.8 1424.0–1437.6 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1430.3 1420.4–1440.2 | community | LMArena Leaderboard Dataset | |
| French (style control)older version arena=text · category=french · style_control=true | 1428.8 1414.7–1442.9 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1426.5 1419.8–1433.1 | 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 | 1423.4 1417.1–1429.8 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1421.7 1410.9–1432.6 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1417.5 1408.3–1426.8 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1415.4 1411.7–1419.0 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1411.2 1396.9–1425.5 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1409.4 1390.3–1428.4 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1407.3 1402.0–1412.5 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1404.7 1397.0–1412.5 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1404.6 1399.8–1409.4 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1401.4 1384.8–1418.1 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1393.3 1388.9–1397.7 | 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 | 1383.6 1377.6–1389.5 | 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 | 1372.3 1366.1–1378.6 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1362.2 1355.2–1369.2 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1327.8 1308.6–1347.0 | community | LMArena Leaderboard Dataset | |
| Japanese (style control)older version arena=text · category=japanese · style_control=true | 1277.7 1253.0–1302.4 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | 87.4 % | independent | Artificial Analysis | |
| GPQA Diamond implementation=vals-ai | 86.6 % | independent | Vals AI | |
| Humanity's Last Exam implementation=artificial-analysis | 29.6 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=vals-ai | 80.4 % | independent | Vals AI | |
| MMLU-Pro implementation=vals-ai | 80.4 % | independent | Vals AI |
long context instruction
| AA-LCR | 78.3 % | independent | Artificial Analysis | |
| IFBench | 75.7 % | independent | Artificial Analysis |
professional
| CaseLaw | 60.9 % | independent | Vals AI | |
| CorpFin | 61.2 % | independent | Vals AI | |
| LegalBench | 84.0 % | independent | Vals AI | |
| TaxEval | 66.6 % | independent | Vals AI |
reasoning math
| AIME implementation=vals-ai | 91.0 % | independent | Vals AI |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Minimax M2 7 | Terminal-Bench 2.1 | 55.4 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + Minimax M2 7 | Terminal-Bench Hard | 39.4 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.