Model comparison
INTELLECT-1 vs Yi 6B
Neither INTELLECT-1 nor Yi 6B has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 7 shared benchmarks.
Hugging FaceSummary
- They share 7 benchmarks with published results for both.
- Yi 6B has downloadable open weights; the other is API-only.
Side by side
| INTELLECT-1 | Yi 6B | |
|---|---|---|
| Provider | Hugging Face | 01.AI |
| Noometry Index | — | — |
| Released | 2024-11-29 | 2023-11-02 |
| 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: —, Yi 6B: —
| Benchmark | INTELLECT-1 | Yi 6B |
|---|---|---|
| BIG-Bench Hard | 34.9% | 47.2% |
| Epoch Capabilities Index | 100.86 | 104.77 |
| HellaSwag | 71.4% | 74.4% |
| WinoGrande | 65.8% | 71.3% |
Math Not comparable
INTELLECT-1: —, Yi 6B: —
| Benchmark | INTELLECT-1 | Yi 6B |
|---|---|---|
| GSM8K | 38.6% | 44.9% |
Knowledge Not comparable
INTELLECT-1: —, Yi 6B: —
| Benchmark | INTELLECT-1 | Yi 6B |
|---|---|---|
| ARC (AI2) Challenge | 54.5% | 50.3% |
| MMLU | 49.9% | 64% |
Frequently asked questions
Is INTELLECT-1 better than Yi 6B?
Neither INTELLECT-1 nor Yi 6B has enough public benchmark results to be ranked yet; the rows below show what has been published.
How many benchmarks do INTELLECT-1 and Yi 6B share?
7 benchmarks have published results for both models. INTELLECT-1 has 7 scored results on Noometry and Yi 6B has 7.