Model comparison
Deepseek Coder v2 vs Falcon-180B
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 32.2 on the Noometry Index.
Last verified . 9 shared benchmarks.
DeepSeek
Technology Innovation InstituteSummary
- They share 9 benchmarks with published results for both. Deepseek Coder v2 scores higher in 4 categories and Falcon-180B in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Deepseek Coder v2 leads 36.3 to 25.2.
Side by side
| Deepseek Coder v2 | Falcon-180B | |
|---|---|---|
| Provider | DeepSeek | Technology Innovation Institute |
| Noometry Index | 35.9 | 32.2 |
| Released | 2024-06-17 | 2023-09-06 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Deepseek Coder v2: 38.1 (#183), Falcon-180B: —
| Benchmark | Deepseek Coder v2 | Falcon-180B |
|---|---|---|
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1251 | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 23.6 (#176), Falcon-180B: 19.1 (#269)
| Benchmark | Deepseek Coder v2 | Falcon-180B |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1007 |
| WinoGrande | 83.7% | 87.1% |
| Epoch Capabilities Index | — | 112.13 |
| HellaSwag | — | 89% |
| LAMBADA | — | 79.8% |
| PIQA | — | 84.9% |
Math Not comparable
Deepseek Coder v2: 34.9 (#190), Falcon-180B: —
| Benchmark | Deepseek Coder v2 | Falcon-180B |
|---|---|---|
| GSM8K | 94.5% | 54.4% |
| LMArena Math | 1241 | — |
Knowledge Not comparable
Deepseek Coder v2: 32.3 (#212), Falcon-180B: —
| Benchmark | Deepseek Coder v2 | Falcon-180B |
|---|---|---|
| ARC (AI2) Challenge | 64.3% | 67.8% |
| LMArena Expert | 1181 | — |
| BoolQ | — | 89% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 64.2% |
Multilingual Deepseek Coder v2 leads
Deepseek Coder v2: 36.3 (#240), Falcon-180B: 25.2 (#286)
| Benchmark | Deepseek Coder v2 | Falcon-180B |
|---|---|---|
| LMArena Non-English | 1182 | 1000 |
| LMArena Chinese | 1201 | — |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Russian | 1188 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Deepseek Coder v2 leads
Deepseek Coder v2: 61.7 (#242), Falcon-180B: 53.4 (#286)
| Benchmark | Deepseek Coder v2 | Falcon-180B |
|---|---|---|
| LMArena Instruction Following | 1180 | 1047 |
Long Context Not comparable
Deepseek Coder v2: 37.0 (#224), Falcon-180B: —
| Benchmark | Deepseek Coder v2 | Falcon-180B |
|---|---|---|
| LMArena Longer Query | 1219 | — |
Writing & Preference Deepseek Coder v2 leads
Deepseek Coder v2: 38.2 (#253), Falcon-180B: 29.1 (#295)
| Benchmark | Deepseek Coder v2 | Falcon-180B |
|---|---|---|
| LMArena Text | 1191 | 1054 |
| LMArena Creative Writing | 1120 | 1089 |
| LMArena Multi-Turn | 1177 | 1013 |
Frequently asked questions
Is Deepseek Coder v2 better than Falcon-180B?
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 32.2 on the Noometry Index.
How many benchmarks do Deepseek Coder v2 and Falcon-180B share?
9 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Falcon-180B has 16.