Phi-3-medium-128k-instruct
Phi-3-medium-128k-instruct places in the top three on BABILong.
13
Benchmarks with a score
0
Ranked first, out of five or more models
1
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
- Open Arabic LLM Leaderboard v1 45.7% #26 /55
- Ko-IFEval (Upstage) 33.5% #13 /21
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
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BABILong | 63% | #2 of 6 | Official leaderboard | |
| Open Arabic LLM Leaderboard v1 | 45.7% | #26 of 55 | Official leaderboard | |
| MuSR | 41.3% | #48 of 98 | Official leaderboard | |
| RepoQA | 63.2% | #13 of 22 | Official leaderboard | |
| Ko-IFEval (Upstage) | 33.5% | #13 of 21 | Official leaderboard | |
| MMLU-Pro | 51.9% | #132 of 212 | Official leaderboard | |
| WildBench | 29.6 | #40 of 47 | Official leaderboard | |
| RULER | 81.5% | #13 of 15 | Official leaderboard | |
| Stick to Your Role! | 0.12 | #15 of 15 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BigCodeBench | 43.2% | #40 of 69 | Official leaderboard | |
| BigCodeBench-Hard | 13.2% | #77 of 96 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AfriMed-QA | 75.2% | #1 of 4 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Open LLM Leaderboard v2 | 32.0 | #20 of 99 | Official leaderboard |