Rankings / MiniMax
Minimax M2
released 2025-10-26
BenchAtlas Index
as of 2026-09-11
base configuration
rank #257
10 families · 5 categories · high
Benchmark evidence
27 results
agentic coding
| τ²-Bench | 86.8 % | independent | Artificial Analysis |
coding
| LiveCodeBench v6 implementation=artificial-analysis | 82.6 % | independent | Artificial Analysis | |
| SciCode | 36.1 % | independent | Artificial Analysis |
external indices
| Intelligence Index v4.1 | 18.6 points | independent | Artificial Analysis | |
| AA Math Index | 78.3 points | independent | Artificial Analysis |
human preference
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1390.9 1376.4–1405.5 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1383.9 1371.8–1396.1 | community | LMArena Leaderboard Dataset | |
| Coding (style control)older version arena=text · category=coding · style_control=true | 1382.9 1367.7–1398.2 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1371.9 1361.0–1382.9 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1369.1 1359.1–1379.0 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1361.5 1343.7–1379.3 | 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 | 1357.9 1339.8–1376.1 | 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 | 1349.5 1332.9–1366.2 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1345.7 1337.9–1353.4 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1342.4 1327.7–1357.2 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1337.1 1324.0–1350.2 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1316.4 1306.5–1326.4 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1303.0 1292.2–1313.8 | 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 | 1299.8 1284.0–1315.6 | 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 | 1299.7 1282.5–1317.0 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1286.8 1266.3–1307.3 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | 77.7 % | independent | Artificial Analysis | |
| Humanity's Last Exam implementation=artificial-analysis | 13.7 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=artificial-analysis | 82.0 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | 64.3 % | independent | Artificial Analysis | |
| IFBench | 72.3 % | independent | Artificial Analysis |
reasoning math
| AIME year=2025 · implementation=artificial-analysis | 78.3 % | independent | Artificial Analysis |
Agent + model results
systems, not bare-model scores
| agent + model mini-SWE-agent + Minimax M2 | SWE-bench bash-only | 61.0 % | community | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + Minimax M2 | SWE-bench Verified | 61.0 % | community | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + Minimax M2 | SWE-bench Verified | 0.4 usd_per_task | community | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + Minimax M2 | SWE-bench bash-only | 0.4 usd_per_task | community | SWE-bench Leaderboard |
| agent + model iflow-cli + Minimax M2 | Terminal-Bench 1.0 | 42.0 % | unverified | Terminal-Bench Leaderboard |
| agent + model Artificial Analysis harness + Minimax M2 | Terminal-Bench Hard | 25.8 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.