Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Falcon-7B
Neither DeepSeek-V2 (MoE-236B, May 2024) nor Falcon-7B has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 8 shared benchmarks.
DeepSeek
Technology Innovation InstituteSummary
- They share 8 benchmarks with published results for both.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Falcon-7B | |
|---|---|---|
| Provider | DeepSeek | Technology Innovation Institute |
| Noometry Index | 40.3 | — |
| Released | 2024-05-07 | 2023-04-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139), Falcon-7B: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Falcon-7B |
|---|---|---|
| BigCodeBench Instruct | 48.9% | — |
| BigCodeBench Complete | 59.4% | — |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Falcon-7B: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Falcon-7B |
|---|---|---|
| BIG-Bench Hard | 78.8% | 28.8% |
| Epoch Capabilities Index | 124.77 | 95.1 |
| HellaSwag | 87.1% | 78.1% |
| PIQA | 83.9% | 80.3% |
| WinoGrande | 86.3% | 67.2% |
| LAMBADA | — | 74.9% |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Falcon-7B: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Falcon-7B |
|---|---|---|
| GSM8K | — | 6.8% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Falcon-7B: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Falcon-7B |
|---|---|---|
| ARC (AI2) Challenge | 92.2% | 47.9% |
| MMLU | 78.4% | 35% |
| TriviaQA | 80% | 64.6% |
| BoolQ | — | 75.3% |
| OpenBookQA | — | 51.6% |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Falcon-7B?
Neither DeepSeek-V2 (MoE-236B, May 2024) nor Falcon-7B has enough public benchmark results to be ranked yet; the rows below show what has been published.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Falcon-7B share?
8 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Falcon-7B has 12.