Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Falcon-180B
Falcon-180B has enough public results to be ranked (#260); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 6 shared benchmarks.
DeepSeek
Technology Innovation InstituteSummary
- They share 6 benchmarks with published results for both.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Falcon-180B | |
|---|---|---|
| Provider | DeepSeek | Technology Innovation Institute |
| Noometry Index | 40.3 | 32.2 |
| Released | 2024-05-07 | 2023-09-06 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 16 |
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-180B: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Falcon-180B |
|---|---|---|
| BigCodeBench Instruct | 48.9% | — |
| BigCodeBench Complete | 59.4% | — |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Falcon-180B: 19.1 (#269)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Falcon-180B |
|---|---|---|
| Epoch Capabilities Index | 124.77 | 112.13 |
| HellaSwag | 87.1% | 89% |
| PIQA | 83.9% | 84.9% |
| WinoGrande | 86.3% | 87.1% |
| LMArena Hard Prompts | — | 1007 |
| BIG-Bench Hard | 78.8% | — |
| LAMBADA | — | 79.8% |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Falcon-180B: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Falcon-180B |
|---|---|---|
| GSM8K | — | 54.4% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Falcon-180B: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Falcon-180B |
|---|---|---|
| ARC (AI2) Challenge | 92.2% | 67.8% |
| MMLU | 78.4% | 70.6% |
| BoolQ | — | 89% |
| OpenBookQA | — | 64.2% |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Falcon-180B: 25.2 (#286)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Falcon-180B |
|---|---|---|
| LMArena Non-English | — | 1000 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Falcon-180B: 53.4 (#286)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Falcon-180B |
|---|---|---|
| LMArena Instruction Following | — | 1047 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Falcon-180B: 29.1 (#295)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Falcon-180B |
|---|---|---|
| LMArena Text | — | 1054 |
| LMArena Creative Writing | — | 1089 |
| LMArena Multi-Turn | — | 1013 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Falcon-180B?
Falcon-180B has enough public results to be ranked (#260); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Falcon-180B share?
6 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Falcon-180B has 16.