Model comparison
Phi-3.5-MoE vs Qwen2.5 32B Instruct
Qwen2.5 32B Instruct has enough public results to be ranked (#291); Phi-3.5-MoE does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Microsoft
Alibaba (Qwen)Side by side
| Phi-3.5-MoE | Qwen2.5 32B Instruct | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | — | 29.7 |
| Released | 2024-08-17 | 2024-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 3 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Phi-3.5-MoE: —, Qwen2.5 32B Instruct: 38.1 (#165)
| Benchmark | Phi-3.5-MoE | Qwen2.5 32B Instruct |
|---|---|---|
| BigCodeBench Instruct | — | 45% |
| BigCodeBench Complete | — | 52.3% |
Reasoning Not comparable
Phi-3.5-MoE: —, Qwen2.5 32B Instruct: 18.5 (#262)
| Benchmark | Phi-3.5-MoE | Qwen2.5 32B Instruct |
|---|---|---|
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 128.52 |
| PIQA | 88.6% | — |
Math Not comparable
Phi-3.5-MoE: —, Qwen2.5 32B Instruct: 15.3 (#289)
| Benchmark | Phi-3.5-MoE | Qwen2.5 32B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 7.4% |
| MATH Level 5 | — | 56.1% |
| GSM8K | 88.7% | — |
Knowledge Not comparable
Phi-3.5-MoE: —, Qwen2.5 32B Instruct: 24.9 (#259)
| Benchmark | Phi-3.5-MoE | Qwen2.5 32B Instruct |
|---|---|---|
| GPQA Diamond | — | 46.1% |
| BoolQ | 84.6% | — |
Frequently asked questions
Is Phi-3.5-MoE better than Qwen2.5 32B Instruct?
Qwen2.5 32B Instruct has enough public results to be ranked (#291); Phi-3.5-MoE does not yet, so treat this comparison as directional.
How many benchmarks do Phi-3.5-MoE and Qwen2.5 32B Instruct share?
0 benchmarks have published results for both models. Phi-3.5-MoE has 3 scored results on Noometry and Qwen2.5 32B Instruct has 7.