Model comparison
Falcon-180B vs Qwen2.5 72B Instruct
Falcon-180B and Qwen2.5 72B Instruct score almost the same on the Noometry Index (31.8 vs 31.5), so choose on price, context window or the category you care about most.
Last verified . 12 shared benchmarks.
Technology Innovation Institute
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Falcon-180B scores higher in 0 categories and Qwen2.5 72B Instruct in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 72B Instruct leads 46.9 to 29.3.
Side by side
| Falcon-180B | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Technology Innovation Institute | Alibaba (Qwen) |
| Noometry Index | 31.8 | 31.5 |
| Released | 2023-09-06 | 2024-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.40 |
| Output $ / M tokens | — | $5.60 |
| Results tracked | 16 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, Qwen2.5 72B Instruct: 32.8 (#256)
| Benchmark | Falcon-180B | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| LMArena Coding | — | 1293 |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
Falcon-180B: —, Qwen2.5 72B Instruct: 22.0 (#124)
| Benchmark | Falcon-180B | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Qwen2.5 72B Instruct leads
Falcon-180B: 18.3 (#266), Qwen2.5 72B Instruct: 21.4 (#197)
| Benchmark | Falcon-180B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1007 | 1271 |
| Epoch Capabilities Index | 111.89 | 129.01 |
| HellaSwag | 89% | 84.8% |
| PIQA | 84.9% | 82.6% |
| WinoGrande | 87.1% | 82.3% |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| LAMBADA | 79.8% | — |
Math Not comparable
Falcon-180B: —, Qwen2.5 72B Instruct: 18.1 (#281)
| Benchmark | Falcon-180B | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| LMArena Math | — | 1283 |
| MATH Level 5 | — | 63.2% |
| GSM8K | 54.4% | — |
Knowledge Not comparable
Falcon-180B: —, Qwen2.5 72B Instruct: 26.9 (#247)
| Benchmark | Falcon-180B | Qwen2.5 72B Instruct |
|---|---|---|
| ARC (AI2) Challenge | 67.8% | 94.5% |
| MMLU | 70.6% | 85.3% |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| LMArena Expert | — | 1245 |
| BoolQ | 89% | — |
| OpenBookQA | 64.2% | — |
| TriviaQA | — | 71.9% |
Multilingual Qwen2.5 72B Instruct leads
Falcon-180B: 25.3 (#281), Qwen2.5 72B Instruct: 41.2 (#208)
| Benchmark | Falcon-180B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1000 | 1252 |
| LMArena Chinese | — | 1272 |
| LMArena French | — | 1279 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Russian | — | 1264 |
| LMArena Spanish | — | 1255 |
Instruction Following Qwen2.5 72B Instruct leads
Falcon-180B: 53.6 (#281), Qwen2.5 72B Instruct: 65.7 (#216)
| Benchmark | Falcon-180B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1047 | 1254 |
| IFEval | — | 80.6% |
Long Context Not comparable
Falcon-180B: —, Qwen2.5 72B Instruct: 38.9 (#183)
| Benchmark | Falcon-180B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | — | 1282 |
Writing & Preference Qwen2.5 72B Instruct leads
Falcon-180B: 29.3 (#290), Qwen2.5 72B Instruct: 46.9 (#210)
| Benchmark | Falcon-180B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1054 | 1269 |
| LMArena Creative Writing | 1089 | 1221 |
| LMArena Multi-Turn | 1013 | 1272 |
| WildBench | — | 80.2% |
Frequently asked questions
Is Falcon-180B better than Qwen2.5 72B Instruct?
Falcon-180B and Qwen2.5 72B Instruct score almost the same on the Noometry Index (31.8 vs 31.5), so choose on price, context window or the category you care about most.
How many benchmarks do Falcon-180B and Qwen2.5 72B Instruct share?
12 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Qwen2.5 72B Instruct has 43.