Model comparison
Falcon-180B vs Qwen-14B
Falcon-180B and Qwen-14B score almost the same on the Noometry Index (32.2 vs 31.4), so choose on price, context window or the category you care about most.
Last verified . 13 shared benchmarks.
Technology Innovation Institute
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Falcon-180B scores higher in 2 categories and Qwen-14B in 2 categories; 2 gaps are clear of the uncertainty.
Side by side
| Falcon-180B | Qwen-14B | |
|---|---|---|
| Provider | Technology Innovation Institute | Alibaba (Qwen) |
| Noometry Index | 32.2 | 31.4 |
| Released | 2023-09-06 | 2023-09-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 16 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, Qwen-14B: 31.2 (#288)
| Benchmark | Falcon-180B | Qwen-14B |
|---|---|---|
| LMArena Coding | — | 1071 |
Reasoning Too close to call
Falcon-180B: 19.1 (#269), Qwen-14B: 19.6 (#257)
| Benchmark | Falcon-180B | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1007 | 1027 |
| Epoch Capabilities Index | 112.13 | 113.03 |
| LAMBADA | 79.8% | 71.1% |
| PIQA | 84.9% | 79.9% |
| BIG-Bench Hard | — | 55% |
| HellaSwag | 89% | — |
| WinoGrande | 87.1% | — |
Math Not comparable
Falcon-180B: —, Qwen-14B: 31.2 (#227)
| Benchmark | Falcon-180B | Qwen-14B |
|---|---|---|
| GSM8K | 54.4% | 61.3% |
| LMArena Math | — | 1068 |
Knowledge Not comparable
Falcon-180B: —, Qwen-14B: —
| Benchmark | Falcon-180B | Qwen-14B |
|---|---|---|
| ARC (AI2) Challenge | 67.8% | 84.4% |
| BoolQ | 89% | 86.2% |
| MMLU | 70.6% | 66.3% |
| OpenBookQA | 64.2% | — |
Multilingual Qwen-14B leads
Falcon-180B: 25.2 (#286), Qwen-14B: 27.5 (#275)
| Benchmark | Falcon-180B | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1000 | 1041 |
| LMArena Chinese | — | 1077 |
Instruction Following Too close to call
Falcon-180B: 53.4 (#286), Qwen-14B: 52.4 (#289)
| Benchmark | Falcon-180B | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1047 | 1031 |
Long Context Not comparable
Falcon-180B: —, Qwen-14B: 31.3 (#280)
| Benchmark | Falcon-180B | Qwen-14B |
|---|---|---|
| LMArena Longer Query | — | 1028 |
Writing & Preference Falcon-180B leads
Falcon-180B: 29.1 (#295), Qwen-14B: 27.6 (#299)
| Benchmark | Falcon-180B | Qwen-14B |
|---|---|---|
| LMArena Text | 1054 | 1051 |
| LMArena Creative Writing | 1089 | 1028 |
| LMArena Multi-Turn | 1013 | 1022 |
Frequently asked questions
Is Falcon-180B better than Qwen-14B?
Falcon-180B and Qwen-14B score almost the same on the Noometry Index (32.2 vs 31.4), so choose on price, context window or the category you care about most.
How many benchmarks do Falcon-180B and Qwen-14B share?
13 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Qwen-14B has 18.