Rankings / MiniMax
Minimax M2 7
released 2026-03-18
BenchAtlas Index
as of 2026-07-14
base configuration
rank #154
7 families · 4 categories · medium
base configuration
rank #218
7 families · 3 categories · medium
Benchmark evidence
46 results
agentic coding
| τ²-Bench | 84.8 % | independent | Artificial Analysis | |
| τ²-Bench subset=banking | 8.9 % | independent | Artificial Analysis |
coding
| SciCode | 47.0 % | independent | Artificial Analysis |
external indices
| AA Coding Index | 52.6 points | independent | Artificial Analysis | |
| Intelligence Index v4.1 | 38.1 points | independent | Artificial Analysis | |
| ECI | 145.6 points | independent | Epoch AI Benchmarking Hub | |
| Vals Index | 41.6 points | independent | Vals AI |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1479.3 1472.8–1485.7 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1469.6 1463.9–1475.3 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1459.0 1452.7–1465.3 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1448.3 1438.2–1458.4 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1442.6 1437.6–1447.7 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1442.0 1428.4–1455.5 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1440.2 1427.4–1453.0 | community | LMArena Leaderboard Dataset | |
| French (style control)older version arena=text · category=french · style_control=true | 1438.5 1421.6–1455.3 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1437.7 1432.3–1443.2 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1434.3 1428.4–1440.3 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1434.2 1422.4–1445.9 | 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 | 1431.8 1423.9–1439.7 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1428.0 1420.3–1435.6 | 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 | 1427.8 1420.5–1435.1 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1426.6 1415.7–1437.5 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1423.6 1411.3–1436.0 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1420.3 1403.3–1437.4 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1416.7 1412.4–1420.9 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1409.2 1403.0–1415.3 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1408.6 1385.6–1431.7 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1406.0 1400.4–1411.5 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1400.8 1391.8–1409.9 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1400.2 1381.1–1419.3 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1392.2 1387.0–1397.3 | 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 | 1384.4 1377.6–1391.3 | 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 | 1373.0 1365.6–1380.3 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1362.6 1354.5–1370.8 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1331.6 1308.1–1355.1 | 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 | 28.1 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=vals-ai | 80.4 % | independent | Vals AI |
long context instruction
| AA-LCR | 68.7 % | 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.