Model comparison
INTELLECT-1 vs Phi-1.5
Neither INTELLECT-1 nor Phi-1.5 has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 5 shared benchmarks.
Hugging Face
MicrosoftSummary
- They share 5 benchmarks with published results for both.
- Phi-1.5 has downloadable open weights; the other is API-only.
Side by side
| INTELLECT-1 | Phi-1.5 | |
|---|---|---|
| Provider | Hugging Face | Microsoft |
| Noometry Index | — | — |
| Released | 2024-11-29 | 2023-09-11 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Reasoning Not comparable
INTELLECT-1: —, Phi-1.5: —
| Benchmark | INTELLECT-1 | Phi-1.5 |
|---|---|---|
| Epoch Capabilities Index | 100.86 | 91.53 |
| HellaSwag | 71.4% | 47.6% |
| WinoGrande | 65.8% | 73.4% |
| BIG-Bench Hard | 34.9% | — |
Math Not comparable
INTELLECT-1: —, Phi-1.5: —
| Benchmark | INTELLECT-1 | Phi-1.5 |
|---|---|---|
| GSM8K | 38.6% | — |
Knowledge Not comparable
INTELLECT-1: —, Phi-1.5: —
| Benchmark | INTELLECT-1 | Phi-1.5 |
|---|---|---|
| ARC (AI2) Challenge | 54.5% | 44.4% |
| MMLU | 49.9% | 37.6% |
| BoolQ | — | 75.8% |
| OpenBookQA | — | 37.2% |
Frequently asked questions
Is INTELLECT-1 better than Phi-1.5?
Neither INTELLECT-1 nor Phi-1.5 has enough public benchmark results to be ranked yet; the rows below show what has been published.
How many benchmarks do INTELLECT-1 and Phi-1.5 share?
5 benchmarks have published results for both models. INTELLECT-1 has 7 scored results on Noometry and Phi-1.5 has 7.