← Leaderboard
Xiaomi · Open weights · tested 10 Oct 2026
MiMo V2.6 Pro High effort
Overall rank#6 of 25
Solves56/10051 first attempt · +5 retry
Rungs proven277/400255 first attempt · +22 retry
Cost to run$10.69$0.19 per solve
Tokens used204.4M91.8% from cache · 6.4M output
Time per lab18.5 minaverage of 140 attempts
Where it places
Each line is one metric across all 25 configurations. Right is always better; this model is the large dot.
Solveslabs solved, of 100
worsebetter
56#6 of 25
Rungs provenrungs proven, of 400
worsebetter
277#6 of 25
First-attempt solvessolved on the first attempt
worsebetter
51#5 of 25
Cost per solveUSD per solved lab
worsebetter
$0.19#2 of 15
By vulnerability class
How MiMo V2.6 Pro (High) did on each type of vulnerability. Shown as counts, because some classes have only a few labs.
- Authentication / authorisation bypass18 of 28 solved90 of 112 rungs
- Information disclosure9 of 12 solved37 of 48 rungs
- IDOR6 of 11 solved30 of 44 rungs
- SSRF0 of 10 solved8 of 40 rungs
- Business logic5 of 10 solved29 of 40 rungs
- Key or secret exposure8 of 8 solved32 of 32 rungs
- XSS5 of 6 solved21 of 24 rungs
- Token theft4 of 5 solved17 of 20 rungs
Fewer than 5 labs each: one lab changes these a lot, so read them with care.
- Supply chain0 of 4 solved6 of 16 rungs
- Remote code execution0 of 3 solved1 of 12 rungs
- SQL injection1 of 2 solved4 of 8 rungs
- File inclusion0 of 1 solved2 of 4 rungs
Provider performance
Measured per single agent against the provider endpoint used for the run.
- Response time
- 20.98 s median · 71.50 s p95
- Output speed
- 38.6 tok/s
- API success rate
- 97.39%
- Input context
- 20.5K median · 84.3K p95
About this result
Every model runs in the same neutral harness, so results compare the models themselves.
- Harness
- BB Arena neutral harness
- Safety refusals
- None