Model comparison
Falcon-180B vs Qwen1.5-14B
Falcon-180B and Qwen1.5-14B score almost the same on the Noometry Index (32.2 vs 32.7), so choose on price, context window or the category you care about most.
Last verified . 7 shared benchmarks.
Technology Innovation Institute
Alibaba (Qwen)Summary
- They share 7 benchmarks with published results for both. Falcon-180B scores higher in 0 categories and Qwen1.5-14B in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen1.5-14B leads 30.7 to 25.2.
Side by side
| Falcon-180B | Qwen1.5-14B | |
|---|---|---|
| Provider | Technology Innovation Institute | Alibaba (Qwen) |
| Noometry Index | 32.2 | 32.7 |
| Released | 2023-09-06 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 16 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, Qwen1.5-14B: 33.1 (#263)
| Benchmark | Falcon-180B | Qwen1.5-14B |
|---|---|---|
| LMArena Coding | — | 1138 |
Reasoning Qwen1.5-14B leads
Falcon-180B: 19.1 (#269), Qwen1.5-14B: 21.4 (#223)
| Benchmark | Falcon-180B | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1007 | 1113 |
| Epoch Capabilities Index | 112.13 | — |
| HellaSwag | 89% | — |
| LAMBADA | 79.8% | — |
| PIQA | 84.9% | — |
| WinoGrande | 87.1% | — |
Math Not comparable
Falcon-180B: —, Qwen1.5-14B: 32.4 (#215)
| Benchmark | Falcon-180B | Qwen1.5-14B |
|---|---|---|
| LMArena Math | — | 1125 |
| GSM8K | 54.4% | — |
Knowledge Not comparable
Falcon-180B: —, Qwen1.5-14B: 29.8 (#232)
| Benchmark | Falcon-180B | Qwen1.5-14B |
|---|---|---|
| MMLU | 70.6% | 68.6% |
| LMArena Expert | — | 1094 |
| ARC (AI2) Challenge | 67.8% | — |
| BoolQ | 89% | — |
| OpenBookQA | 64.2% | — |
Multilingual Qwen1.5-14B leads
Falcon-180B: 25.2 (#286), Qwen1.5-14B: 30.7 (#262)
| Benchmark | Falcon-180B | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 1000 | 1095 |
| LMArena Chinese | — | 1147 |
| LMArena French | — | 1116 |
| LMArena German | — | 1043 |
| LMArena Japanese | — | 1019 |
| LMArena Russian | — | 1046 |
| LMArena Spanish | — | 1085 |
Instruction Following Qwen1.5-14B leads
Falcon-180B: 53.4 (#286), Qwen1.5-14B: 56.8 (#271)
| Benchmark | Falcon-180B | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1047 | 1102 |
Long Context Not comparable
Falcon-180B: —, Qwen1.5-14B: 33.7 (#257)
| Benchmark | Falcon-180B | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | — | 1113 |
Writing & Preference Qwen1.5-14B leads
Falcon-180B: 29.1 (#295), Qwen1.5-14B: 33.6 (#276)
| Benchmark | Falcon-180B | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1054 | 1128 |
| LMArena Creative Writing | 1089 | 1091 |
| LMArena Multi-Turn | 1013 | 1110 |
Frequently asked questions
Is Falcon-180B better than Qwen1.5-14B?
Falcon-180B and Qwen1.5-14B score almost the same on the Noometry Index (32.2 vs 32.7), so choose on price, context window or the category you care about most.
How many benchmarks do Falcon-180B and Qwen1.5-14B share?
7 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Qwen1.5-14B has 17.