Phi 3 Small 8k Instruct — Benchmarks
Benchmark scores for Phi 3 Small 8k Instruct aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
No overall rank for Phi 3 Small 8k Instruct: an overall score is only published when a model has been measured on enough of the benchmarks current models are still submitted to. Its individual scores below stand on their own — see the methodology for how the overall score is built.
Instruction Following
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| LMArena Text | 1170.8 | #155 / 182 | #342 / 391 |
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| ARC Challenge | 90.7% | #6 / 56 | #6 / 76 |
| OpenBookQA | 88.0% | #2 / 26 | #2 / 41 |
| TriviaQA | 58.1% | #17 / 19 | #36 / 39 |
| MMLU | 75.7% | #20 / 85 | #43 / 136 |
| HellaSwag | 77.0% | #20 / 47 | #38 / 75 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| WinoGrande | 81.5% | #9 / 51 | #17 / 79 |
| BIG-Bench Hard | 79.1% | #5 / 38 | #7 / 50 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.