Model comparison
INTELLECT-1 vs Llama 2-34B
Neither INTELLECT-1 nor Llama 2-34B has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 6 shared benchmarks.
Hugging Face
MetaSummary
- They share 6 benchmarks with published results for both.
Side by side
| INTELLECT-1 | Llama 2-34B | |
|---|---|---|
| Provider | Hugging Face | Meta |
| Noometry Index | — | — |
| Released | 2024-11-29 | 2023-07-18 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Reasoning Not comparable
INTELLECT-1: —, Llama 2-34B: —
| Benchmark | INTELLECT-1 | Llama 2-34B |
|---|---|---|
| BIG-Bench Hard | 34.9% | 44.1% |
| Epoch Capabilities Index | 100.86 | 105.2 |
| WinoGrande | 65.8% | 76.7% |
| HellaSwag | 71.4% | — |
| PIQA | — | 81.9% |
Math Not comparable
INTELLECT-1: —, Llama 2-34B: —
| Benchmark | INTELLECT-1 | Llama 2-34B |
|---|---|---|
| GSM8K | 38.6% | 42.2% |
Knowledge Not comparable
INTELLECT-1: —, Llama 2-34B: —
| Benchmark | INTELLECT-1 | Llama 2-34B |
|---|---|---|
| ARC (AI2) Challenge | 54.5% | 54.5% |
| MMLU | 49.9% | 62.6% |
| BoolQ | — | 83.7% |
| OpenBookQA | — | 58.2% |
| TriviaQA | — | 84.6% |
Frequently asked questions
Is INTELLECT-1 better than Llama 2-34B?
Neither INTELLECT-1 nor Llama 2-34B has enough public benchmark results to be ranked yet; the rows below show what has been published.
How many benchmarks do INTELLECT-1 and Llama 2-34B share?
6 benchmarks have published results for both models. INTELLECT-1 has 7 scored results on Noometry and Llama 2-34B has 10.