Phi-3-mini-128k-instruct
Phi-3-mini-128k-instruct.
11
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Microsoft Apr 2024 Phi-3-mini-128k-instruct
Open weights Small
No Epoch Capabilities Index score yet
- StructEval 40.8% #28 /28
- Vectara Hallucination Leaderboard (HHEM) 3.10% #101 /148
- BigCodeBench-Hard 10.8% #82 /96
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 | |
|---|---|---|---|---|
| Vectara Hallucination Leaderboard (HHEM) | 3.10% | #101 of 148 | Official leaderboard | |
| MMLU-Pro | 43.9% | #149 of 212 | Official leaderboard | |
| RepoQA | 22.4% | #20 of 22 | Official leaderboard | |
| WildBench | 25.7 | #43 of 47 | Official leaderboard | |
| LMArena (Elo) | 1,130 | #314 of 333 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BigCodeBench | 35.1% | #56 of 69 | Official leaderboard | |
| BigCodeBench-Hard | 10.8% | #82 of 96 | Official leaderboard | |
| StructEval | 40.8% | #28 of 28 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SuperCLUE-Agent | 55.3 | #6 of 7 | Official leaderboard | |
| AceBench | 32% | #15 of 16 | Official leaderboard | |
| SnakeBench | 12 | #174 of 183 | Official leaderboard |