Model comparison
DeepSeek-V2.5 (Sep 2024) vs Falcon-180B
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 32.2 on the Noometry Index.
Last verified . 6 shared benchmarks.
DeepSeek
Technology Innovation InstituteSummary
- They share 6 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 4 categories and Falcon-180B in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V2.5 (Sep 2024) leads 49.8 to 29.1.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Falcon-180B | |
|---|---|---|
| Provider | DeepSeek | Technology Innovation Institute |
| Noometry Index | 37.6 | 32.2 |
| Released | 2024-09-06 | 2023-09-06 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Falcon-180B: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Falcon-180B |
|---|---|---|
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| LMArena Coding | 1309 | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Falcon-180B: 19.1 (#269)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Falcon-180B |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1007 |
| Epoch Capabilities Index | — | 112.13 |
| HellaSwag | — | 89% |
| LAMBADA | — | 79.8% |
| PIQA | — | 84.9% |
| WinoGrande | — | 87.1% |
Math Not comparable
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Falcon-180B: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Falcon-180B |
|---|---|---|
| LMArena Math | 1288 | — |
| GSM8K | — | 54.4% |
Knowledge Not comparable
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Falcon-180B: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Falcon-180B |
|---|---|---|
| LMArena Expert | 1266 | — |
| ARC (AI2) Challenge | — | 67.8% |
| BoolQ | — | 89% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 64.2% |
Multilingual DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Falcon-180B: 25.2 (#286)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Falcon-180B |
|---|---|---|
| LMArena Non-English | 1273 | 1000 |
| LMArena Chinese | 1318 | — |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Russian | 1289 | — |
| LMArena Spanish | 1248 | — |
Instruction Following DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Falcon-180B: 53.4 (#286)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Falcon-180B |
|---|---|---|
| LMArena Instruction Following | 1280 | 1047 |
Long Context Not comparable
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Falcon-180B: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Falcon-180B |
|---|---|---|
| LMArena Longer Query | 1301 | — |
Writing & Preference DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Falcon-180B: 29.1 (#295)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Falcon-180B |
|---|---|---|
| LMArena Text | 1294 | 1054 |
| LMArena Creative Writing | 1285 | 1089 |
| LMArena Multi-Turn | 1297 | 1013 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Falcon-180B?
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 32.2 on the Noometry Index.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Falcon-180B share?
6 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Falcon-180B has 16.