BenchAtlas

Rankings / xiaomi

Mimo V2 5 Pro

open weights

released 2026-04-22

BenchAtlas Index

as of 2026-07-14
68.1
base configuration
rank #75
7 families · 4 categories · medium
59.8
base configuration
rank #149
6 families · 3 categories · medium
52.8
no reasoning
rank #196
7 families · 4 categories · medium

Benchmark evidence

50 results
agentic coding
τ²-Bench94.2 %independentArtificial Analysis
τ²-Benchno reasoning72.5 %independentArtificial Analysis
τ²-Bench
subset=banking
8.7 %independentArtificial Analysis
coding
SciCode50.2 %independentArtificial Analysis
SciCodeno reasoning39.1 %independentArtificial Analysis
external indices
AA Coding Index60.2 pointsindependentArtificial Analysis
Intelligence Index v4.142.2 pointsindependentArtificial Analysis
Intelligence Index v4.1no reasoning27.9 pointsindependentArtificial Analysis
Vals Index50.7 pointsindependentVals AI
human preference
Coding (style control)older version
arena=text · category=coding · style_control=true
1519.0
1511.7–1526.2
communityLMArena Leaderboard Dataset
Chinese (style control)older version
arena=text · category=chinese · style_control=true
1515.5
1501.0–1530.1
communityLMArena Leaderboard Dataset
Expert (style control)older version
arena=text · category=expert · style_control=true
1511.0
1500.1–1522.0
communityLMArena Leaderboard Dataset
Hard Prompts English (style control)older version
arena=text · category=hard_prompts_english · style_control=true
1505.3
1498.5–1512.2
communityLMArena Leaderboard Dataset
Industry Software And It Services (style control)older version
arena=text · category=industry_software_and_it_services · style_control=true
1504.3
1498.0–1510.6
communityLMArena Leaderboard Dataset
French (style control)older version
arena=text · category=french · style_control=true
1499.5
1481.4–1517.5
communityLMArena Leaderboard Dataset
Industry Mathematical (style control)older version
arena=text · category=industry_mathematical · style_control=true
1496.7
1482.6–1510.8
communityLMArena Leaderboard Dataset
Hard Prompts (style control)older version
arena=text · category=hard_prompts · style_control=true
1494.3
1488.9–1499.8
communityLMArena 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
1491.9
1483.6–1500.3
communityLMArena Leaderboard Dataset
Longer Query (style control)older version
arena=text · category=longer_query · style_control=true
1486.7
1480.2–1493.1
communityLMArena Leaderboard Dataset
Industry Medicine And Healthcare (style control)older version
arena=text · category=industry_medicine_and_healthcare · style_control=true
1482.7
1470.5–1495.0
communityLMArena Leaderboard Dataset
English (style control)older version
arena=text · category=english · style_control=true
1482.7
1476.8–1488.6
communityLMArena Leaderboard Dataset
Industry Legal And Government (style control)older version
arena=text · category=industry_legal_and_government · style_control=true
1478.6
1467.0–1490.1
communityLMArena Leaderboard Dataset
Math (style control)older version
arena=text · category=math · style_control=true
1477.7
1463.8–1491.5
communityLMArena Leaderboard Dataset
Multi Turn (style control)older version
arena=text · category=multi_turn · style_control=true
1476.7
1468.5–1485.0
communityLMArena 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
1471.5
1463.7–1479.4
communityLMArena Leaderboard Dataset
Instruction Following (style control)older version
arena=text · category=instruction_following · style_control=true
1471.5
1464.8–1478.2
communityLMArena Leaderboard Dataset
Exclude Ties (style control)older version
arena=text · category=exclude_ties · style_control=true
1470.5
1464.6–1476.4
communityLMArena Leaderboard Dataset
Overall (style control)
arena=text · category=overall · style_control=true
1465.6
1461.0–1470.2
communityLMArena Leaderboard Dataset
Polish (style control)older version
arena=text · category=polish · style_control=true
1464.9
1443.1–1486.7
communityLMArena Leaderboard Dataset
German (style control)older version
arena=text · category=german · style_control=true
1458.0
1433.5–1482.6
communityLMArena Leaderboard Dataset
Russian (style control)older version
arena=text · category=russian · style_control=true
1457.4
1447.6–1467.2
communityLMArena Leaderboard Dataset
Spanish (style control)older version
arena=text · category=spanish · style_control=true
1455.3
1436.5–1474.2
communityLMArena Leaderboard Dataset
Industry Writing And Literature And Language (style control)older version
arena=text · category=industry_writing_and_literature_and_language · style_control=true
1450.2
1443.0–1457.5
communityLMArena Leaderboard Dataset
Non English (style control)older version
arena=text · category=non_english · style_control=true
1446.8
1441.2–1452.4
communityLMArena Leaderboard Dataset
Industry Entertainment And Sports And Media (style control)older version
arena=text · category=industry_entertainment_and_sports_and_media · style_control=true
1440.9
1433.1–1448.6
communityLMArena Leaderboard Dataset
Korean (style control)older version
arena=text · category=korean · style_control=true
1438.3
1413.3–1463.3
communityLMArena Leaderboard Dataset
Creative Writing (style control)older version
arena=text · category=creative_writing · style_control=true
1432.9
1424.5–1441.4
communityLMArena Leaderboard Dataset
knowledge science
GPQA Diamond
implementation=artificial-analysis
86.6 %independentArtificial Analysis
GPQA Diamond
implementation=vals-ai
82.6 %independentVals AI
GPQA Diamond
implementation=artificial-analysis
no reasoning76.2 %independentArtificial Analysis
Humanity's Last Exam
implementation=artificial-analysis
33.8 %independentArtificial Analysis
Humanity's Last Exam
implementation=artificial-analysis
no reasoning13.3 %independentArtificial Analysis
MMLU-Pro
implementation=vals-ai
84.6 %independentVals AI
long context instruction
AA-LCR73.3 %independentArtificial Analysis
AA-LCRno reasoning35.0 %independentArtificial Analysis
IFBench79.9 %independentArtificial Analysis
IFBenchno reasoning42.7 %independentArtificial Analysis
professional
CorpFin61.4 %independentVals AI
LegalBench77.1 %independentVals AI
TaxEval73.8 %independentVals AI

Agent + model results

systems, not bare-model scores
agent + model Artificial Analysis harness + Mimo V2 5 ProTerminal-Bench 2.165.2 %independentArtificial Analysis
agent + model Artificial Analysis harness + Mimo V2 5 ProTerminal-Bench Hard43.2 %independentArtificial Analysis
agent + model Artificial Analysis harness + Mimo V2 5 ProTerminal-Bench Hard35.6 %independentArtificial Analysis

These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.