Benchmark Almanac

Ministral 8B

Ministral 8B.

Mistral AI Released 16 Oct 2024
19
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Mistral AI Oct 2024

Ministral 8B

Open weights

No Epoch Capabilities Index score yet
  • SimpleQA Verified 6.82% #51 /56
  • GPQA Diamond 27.1% #206 /219
  • Vectara Hallucination Leaderboard (HHEM) 7.50% #35 /148

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
Vectara Hallucination Leaderboard (HHEM) 7.50% #35 of 148 Official leaderboard
Vectara Hallucination Leaderboard (2025 dataset) 7.40% #35 of 104 Official leaderboard
FaithJudge 30.9% #29 of 37 Official leaderboard
MMLU-Pro 37.9% #168 of 212 Official leaderboard
LMArena (Elo) 1,238 #265 of 333 Official leaderboard
BuzzBench 32.3 #20 of 23 Official leaderboard
SimpleQA Verified 6.82% #51 of 56 Official leaderboard
ECLeKTic 3.98% #32 of 35 Official leaderboard
FACTS Grounding 56.1% #33 of 34 Official leaderboard

Math and science

BenchmarkScoreRankSource
MATH Level 5 14.9% #81 of 94 Epoch AI
GPQA Diamond 27.1% #206 of 219 Epoch AI
U-MATH 23.1% #29 of 30 Official leaderboard
DTBench 45.7% #173 of 177 Epoch AI

Agents and tools

BenchmarkScoreRankSource
Berkeley Function Calling Leaderboard (BFCL) 51.5% #47 of 67 Official leaderboard
SnakeBench 19 #141 of 183 Official leaderboard
Galileo Agent Leaderboard 0.69 #29 of 31 Official leaderboard
BFCL V4 11.1% #61 of 65 Official leaderboard

Professional work

BenchmarkScoreRankSource
LEXam 14.9% #30 of 31 Official leaderboard

Safety and security

BenchmarkScoreRankSource
BaxBench 1.89% #32 of 34 Official leaderboard