Phi-3-mini-128k-instruct
Phi-3-mini-128k-instruct.
17
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
- BigCodeBench-Hard 10.8% #82 /96
- BABILong 52.1% #4 /6
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% | #48 of 148 | Official leaderboard | |
| MuSR | 39.4% | #62 of 98 | Official leaderboard | |
| BABILong | 52.1% | #4 of 6 | Official leaderboard | |
| MMLU-Pro | 43.9% | #149 of 212 | Official leaderboard | |
| RULER | 84.8% | #12 of 15 | Official leaderboard | |
| Arena-Hard-Auto | 15.4% | #34 of 38 | Official leaderboard | |
| RepoQA | 22.4% | #20 of 22 | Official leaderboard | |
| WildBench | 25.7 | #43 of 47 | Official leaderboard | |
| LMArena (Elo) | 1,130 | #316 of 335 | 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 | #180 of 188 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AfriMed-QA | 68.1% | #2 of 4 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Open LLM Leaderboard v2 | 26.3 | #36 of 99 | Official leaderboard |