← Leaderboard
Mistral · Proprietary · tested 11 Oct 2026
Mistral Large 4.0 High effort
Overall rank#8 of 25
Solves52/10049 first attempt · +3 retry
Rungs proven266/400253 first attempt · +13 retry
Cost to run$68.36$1.31 per solve
Tokens used412.2M88.9% from cache · 8.2M output
Time per lab18.8 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
52#8 of 25
Rungs provenrungs proven, of 400
worsebetter
266#8 of 25
First-attempt solvessolved on the first attempt
worsebetter
49#7 of 25
Cost per solveUSD per solved lab
worsebetter
$1.31#7 of 15
By vulnerability class
How Mistral Large 4.0 (High) did on each type of vulnerability. Shown as counts, because some classes have only a few labs.
- Authentication / authorisation bypass16 of 28 solved82 of 112 rungs
- Information disclosure8 of 12 solved33 of 48 rungs
- IDOR3 of 11 solved27 of 44 rungs
- SSRF0 of 10 solved8 of 40 rungs
- Business logic6 of 10 solved32 of 40 rungs
- Key or secret exposure8 of 8 solved32 of 32 rungs
- XSS4 of 6 solved17 of 24 rungs
- Token theft5 of 5 solved20 of 20 rungs
Fewer than 5 labs each: one lab changes these a lot, so read them with care.
- Supply chain1 of 4 solved8 of 16 rungs
- Remote code execution0 of 3 solved1 of 12 rungs
- SQL injection1 of 2 solved5 of 8 rungs
- File inclusion0 of 1 solved1 of 4 rungs
Provider performance
Measured per single agent against the provider endpoint used for the run.
- Response time
- 10.27 s median · 41.76 s p95
- Output speed
- 68.5 tok/s
- API success rate
- 99.31%
- Input context
- 35.0K median · 141.7K 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