Model comparison
Falcon-180B vs Qwen2-72B
Falcon-180B is the stronger model overall, scoring 32.2 to 30.0 on the Noometry Index.
Last verified . 8 shared benchmarks.
Technology Innovation Institute
Alibaba (Qwen)Summary
- They share 8 benchmarks with published results for both. Falcon-180B scores higher in 0 categories and Qwen2-72B in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2-72B leads 40.8 to 29.1.
Side by side
| Falcon-180B | Qwen2-72B | |
|---|---|---|
| Provider | Technology Innovation Institute | Alibaba (Qwen) |
| Noometry Index | 32.2 | 30.0 |
| Released | 2023-09-06 | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 16 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, Qwen2-72B: 29.1 (#310)
| Benchmark | Falcon-180B | Qwen2-72B |
|---|---|---|
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| LMArena Coding | — | 1196 |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Falcon-180B: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Falcon-180B | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Falcon-180B: 19.1 (#269), Qwen2-72B: 23.2 (#181)
| Benchmark | Falcon-180B | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1007 | 1191 |
| Epoch Capabilities Index | 112.13 | 125.28 |
| HellaSwag | 89% | — |
| LAMBADA | 79.8% | — |
| PIQA | 84.9% | — |
| WinoGrande | 87.1% | — |
Math Not comparable
Falcon-180B: —, Qwen2-72B: 30.2 (#236)
| Benchmark | Falcon-180B | Qwen2-72B |
|---|---|---|
| LMArena Math | — | 1235 |
| MATH Level 5 | — | 39.1% |
| GSM8K | 54.4% | — |
Knowledge Not comparable
Falcon-180B: —, Qwen2-72B: 21.2 (#275)
| Benchmark | Falcon-180B | Qwen2-72B |
|---|---|---|
| MMLU | 70.6% | 82.4% |
| GPQA Diamond | — | 40.8% |
| LMArena Expert | — | 1171 |
| ARC (AI2) Challenge | 67.8% | — |
| BoolQ | 89% | — |
| OpenBookQA | 64.2% | — |
Multilingual Qwen2-72B leads
Falcon-180B: 25.2 (#286), Qwen2-72B: 35.9 (#244)
| Benchmark | Falcon-180B | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1000 | 1176 |
| LMArena Chinese | — | 1240 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Russian | — | 1169 |
| LMArena Spanish | — | 1169 |
Instruction Following Qwen2-72B leads
Falcon-180B: 53.4 (#286), Qwen2-72B: 61.7 (#241)
| Benchmark | Falcon-180B | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1047 | 1181 |
Long Context Not comparable
Falcon-180B: —, Qwen2-72B: 36.1 (#235)
| Benchmark | Falcon-180B | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | — | 1192 |
Writing & Preference Qwen2-72B leads
Falcon-180B: 29.1 (#295), Qwen2-72B: 40.8 (#241)
| Benchmark | Falcon-180B | Qwen2-72B |
|---|---|---|
| LMArena Text | 1054 | 1203 |
| LMArena Creative Writing | 1089 | 1181 |
| LMArena Multi-Turn | 1013 | 1196 |
Frequently asked questions
Is Falcon-180B better than Qwen2-72B?
Falcon-180B is the stronger model overall, scoring 32.2 to 30.0 on the Noometry Index.
How many benchmarks do Falcon-180B and Qwen2-72B share?
8 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Qwen2-72B has 26.