Benchmark Almanac

MiMo-V2.6 Flash

MiMo-V2.6 Flash places in the top three on 2 benchmarks.

Xiaomi Corp Released September 21st, 2026 Compare with others
51
Benchmarks with a score
0
Ranked first, out of five or more models
2
In the top three
Xiaomi Corp Sep 2026

MiMo-V2.6 Flash

No Epoch Capabilities Index score yet
  • Terminal-Bench 4.0 16.1% #29 /40
  • Harvey LAB (Legal Agent Benchmark) 11.3% #16 /80
  • Vals Finance Agent v2 56.3% #21 /80

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
LMArena (Elo) 1,448 #67 of 335 Official leaderboard
StudyArena Text 1,199 #63 of 85 Official leaderboard

Math and science

BenchmarkScoreRankSource
ProofBench v1.1 63% #22 of 52 Official leaderboard
BioMysteryBench 69.3% #18 of 30 Official leaderboard
MysteryMechanism 21.6% #24 of 31 Official leaderboard

Coding

BenchmarkScoreRankSource
StructEval 79.6% #3 of 28 Official leaderboard
Code Arena 1,638 #22 of 128 Official leaderboard
Claw-SWE-Bench 74.6% #4 of 16 Official leaderboard
Vibe Code Bench 79% #35 of 120 Official leaderboard
Image-to-WebDev Arena 1,593 #18 of 55 Official leaderboard
Doc2Harness 41.9% #7 of 19 Official leaderboard
Code Migration 40.9% #30 of 78 Official leaderboard
ALE-Bench 1,455 #62 of 126 Official leaderboard
MiMo Code Bench 61.2% #4 of 8 Official leaderboard
MiMo Visual Coding 71.5% #5 of 9 Official leaderboard
IOI v2 (Vals) 47.7% #28 of 45 Official leaderboard
Code Migration v1.1 39.5% #21 of 30 Official leaderboard
DAXBench v2 58.9% #46 of 47 Official leaderboard

Agents and tools

BenchmarkScoreRankSource
Agent Arena -0.03% #33 of 56 Official leaderboard
Terminal-Bench 4.1 16.1% #30 of 43 Official leaderboard
DuelLab GameBench 2 59.0 #40 of 57 Official leaderboard
Terminal-Bench 4.0 16.1% #29 of 40 Official leaderboard

Professional work

BenchmarkScoreRankSource
Harvey LAB (Legal Agent Benchmark) 11.3% #16 of 80 Official leaderboard
Vals Index v2 59.6% #16 of 65 Official leaderboard
Vals Finance Agent v2 56.3% #21 of 80 Official leaderboard
Public Benefits Bench 67.6% #14 of 50 Official leaderboard
MedScribe 85.3% #29 of 97 Official leaderboard
Excel Modeling Benchmark 65.5% #24 of 76 Official leaderboard
Harvey LAB v1.1 (HLAB-Vals-1.1) 13.3% #15 of 38 Official leaderboard
Vals Finance Agent v2.1 63.3% #17 of 40 Official leaderboard
Vals Index v2.1 53.2% #21 of 49 Official leaderboard
Tax Agent Bench 28.5% #38 of 84 Official leaderboard
Legal Research Bench 38% #46 of 93 Official leaderboard
Vals Finance Index 57.1% #21 of 40 Official leaderboard
MedCode 41.1% #55 of 96 Official leaderboard
Vals Legal Index 69% #23 of 38 Official leaderboard
Excel Modeling Benchmark v1.1 68.9% #26 of 42 Official leaderboard
FoodTruck Bench $13,914 #38 of 59 Official leaderboard
Vals Index v2.2 54.8% #24 of 37 Official leaderboard

Vision, audio and robotics

BenchmarkScoreRankSource
Vision Arena 1,248 #46 of 136 Official leaderboard
Humanity's Sixth Sense 25.4% #26 of 34 Official leaderboard

Safety and security

BenchmarkScoreRankSource
CyberBench v1.1 (Vals) 75.4% #7 of 44 Official leaderboard
MiMo Cyber Bench 77.2% #2 of 5 Official leaderboard
SecIT Bench 76% #11 of 26 Official leaderboard
SRE-Bench 4.20% #17 of 35 Official leaderboard
dfbench 53.5% #9 of 18 Official leaderboard

Other

BenchmarkScoreRankSource
Political Science LLM Benchmark 67.9% #13 of 42 Official leaderboard
SAGE (Vals) 43.5% #48 of 81 Official leaderboard
SAGE v1.1 (Vals) 83.3% #22 of 29 Official leaderboard
Vals Science Index 31.7% #19 of 25 Official leaderboard
SuperCLUE 36.4 #15 of 16 Official leaderboard