Model comparison
Falcon-180B vs Qwen2.5-Coder-32B
Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 32.2 on the Noometry Index.
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-Coder-32B in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen2.5-Coder-32B leads 37.8 to 25.2.
Side by side
| Falcon-180B | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Technology Innovation Institute | Alibaba (Qwen) |
| Noometry Index | 32.2 | 33.4 |
| Released | 2023-09-06 | 2024-09-18 |
| Weights | Open | Open |
| Context window | — | 33K |
| Max output | — | 29K |
| Input $ / M tokens | — | $0.66 |
| Output $ / M tokens | — | $1 |
| Results tracked | 16 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | Falcon-180B | Qwen2.5-Coder-32B |
|---|---|---|
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| LMArena Coding | — | 1276 |
| BigCodeBench Complete | — | 58% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Reasoning Qwen2.5-Coder-32B leads
Falcon-180B: 19.1 (#269), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | Falcon-180B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1007 | 1251 |
| Epoch Capabilities Index | 112.13 | 119.49 |
| HellaSwag | 89% | 83% |
| WinoGrande | 87.1% | 80.8% |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| LAMBADA | 79.8% | — |
| LiveBench | — | 46.2% |
| PIQA | 84.9% | — |
Math Not comparable
Falcon-180B: —, Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | Falcon-180B | Qwen2.5-Coder-32B |
|---|---|---|
| GSM8K | 54.4% | 93% |
| LiveBench Math | — | 46.6% |
| LMArena Math | — | 1251 |
Knowledge Not comparable
Falcon-180B: —, Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | Falcon-180B | Qwen2.5-Coder-32B |
|---|---|---|
| ARC (AI2) Challenge | 67.8% | 70.5% |
| MMLU | 70.6% | 79.1% |
| LMArena Expert | — | 1221 |
| BoolQ | 89% | — |
| OpenBookQA | 64.2% | — |
Multilingual Qwen2.5-Coder-32B leads
Falcon-180B: 25.2 (#286), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | Falcon-180B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1000 | 1205 |
| LMArena Chinese | — | 1222 |
| LMArena Russian | — | 1228 |
Instruction Following Qwen2.5-Coder-32B leads
Falcon-180B: 53.4 (#286), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | Falcon-180B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1047 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context Not comparable
Falcon-180B: —, Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | Falcon-180B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | — | 1251 |
Writing & Preference Qwen2.5-Coder-32B leads
Falcon-180B: 29.1 (#295), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | Falcon-180B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1054 | 1230 |
| LMArena Creative Writing | 1089 | 1174 |
| LMArena Multi-Turn | 1013 | 1222 |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is Falcon-180B better than Qwen2.5-Coder-32B?
Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 32.2 on the Noometry Index.
How many benchmarks do Falcon-180B and Qwen2.5-Coder-32B share?
12 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Qwen2.5-Coder-32B has 31.