Benchmark Almanac

Phi-3-medium-128k-instruct

Phi-3-medium-128k-instruct.

Microsoft Released 21 May 2024 Family Phi-3 The lab's model card
5
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Microsoft May 2024

Phi-3-medium-128k-instruct

Open weights Mid-size

No Epoch Capabilities Index score yet
  • BigCodeBench-Hard 13.2% #77 /96
  • RepoQA 63.2% #13 /22

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
RepoQA 63.2% #13 of 22 Official leaderboard
MMLU-Pro 51.9% #132 of 212 Official leaderboard
WildBench 29.6 #40 of 47 Official leaderboard

Coding

BenchmarkScoreRankSource
BigCodeBench 43.2% #40 of 69 Official leaderboard
BigCodeBench-Hard 13.2% #77 of 96 Official leaderboard