Benchmark Almanac

AFM-4.5B

AFM-4.5B.

Arcee AI Released 29 Jul 2025 Family AFM The lab's model card
8
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Arcee AI Jul 2025

AFM-4.5B

Open weights Small

No Epoch Capabilities Index score yet
  • IFEval 67% #119 /126
  • MMLU 65.9% #105 /127
  • AGIEval 30% #33 /35

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 65.9% #105 of 127 Model card
AGIEval 30% #33 of 35 Model card
IFEval 67% #119 of 126 Model card
TriviaQA 47.7% #37 of 39 Model card
MuSR 38.8% #6 of 6 Model card
MixEval 73.8% #2 of 2 Model card

Math and science

BenchmarkScoreRankSource
GPQA Diamond 27.8% #280 of 284 Model card

Agents and tools

BenchmarkScoreRankSource
SnakeBench 13 #171 of 183 Official leaderboard

Its launch post

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