Benchmark Almanac

Trinity Mini

Trinity Mini.

Arcee AI Released 1 Dec 2025 Family Trinity The lab's model card
6
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Arcee AI Dec 2025

Trinity Mini

Open weights Small

No Epoch Capabilities Index score yet
  • MMLU 85% #55 /127
  • Berkeley Function Calling Leaderboard (BFCL) 59.7% #41 /47
  • MATH-500 92.1% #49 /67

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
MMLU 85% #55 of 127 Model card
MuSR 63.5% #5 of 6 Model card
SimpleQA 8.90% #51 of 59 Model card

Math and science

BenchmarkScoreRankSource
MATH-500 92.1% #49 of 67 Model card
GPQA Diamond 58.5% #211 of 284 Model card

Agents and tools

BenchmarkScoreRankSource
Berkeley Function Calling Leaderboard (BFCL) 59.7% #41 of 47 Model card

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.