Model comparison
Phi-4 vs Qwen2.5 Plus 1127
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.8 to 31.2 on the Noometry Index.
Last verified . 14 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. Phi-4 scores higher in 0 categories and Qwen2.5 Plus 1127 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5 Plus 1127 leads 36.1 to 20.8.
- Phi-4 has downloadable open weights; the other is API-only.
Side by side
| Phi-4 | Qwen2.5 Plus 1127 | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 31.2 | 38.8 |
| Released | 2024-12-11 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.07 | — |
| Output $ / M tokens | $0.14 | — |
| Results tracked | 37 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 Plus 1127 leads
Phi-4: 34.4 (#239), Qwen2.5 Plus 1127: 38.5 (#175)
| Benchmark | Phi-4 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Coding | 1231 | 1314 |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 30.7% | — |
| BigCodeBench Complete | 55.4% | — |
Agentic & Tool Use Not comparable
Phi-4: 22.8 (#128), Qwen2.5 Plus 1127: —
| Benchmark | Phi-4 | Qwen2.5 Plus 1127 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.8% | — |
| BALROG | 11.6% | — |
Reasoning Qwen2.5 Plus 1127 leads
Phi-4: 17.7 (#291), Qwen2.5 Plus 1127: 25.9 (#141)
| Benchmark | Phi-4 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1299 |
| Chess Puzzles | 1% | — |
| LiveBench Reasoning | 47.8% | — |
| LiveBench Data Analysis | 45.2% | — |
| Epoch Capabilities Index | 130.42 | — |
| LiveBench | 41.6% | — |
Math Qwen2.5 Plus 1127 leads
Phi-4: 20.8 (#285), Qwen2.5 Plus 1127: 36.1 (#174)
| Benchmark | Phi-4 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Math | 1246 | 1298 |
| OTIS Mock AIME 2024-2025 | 13.8% | — |
| LiveBench Math | 42% | — |
| MATH Level 5 | 64.9% | — |
Knowledge Qwen2.5 Plus 1127 leads
Phi-4: 32.6 (#209), Qwen2.5 Plus 1127: 35.5 (#183)
| Benchmark | Phi-4 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Expert | 1203 | 1289 |
| GPQA Diamond | 56.1% | — |
| Confabulations | 29.4% | — |
| Vectara Hallucination Rate | 3.7% | — |
| MMLU | 84.8% | — |
Multilingual Qwen2.5 Plus 1127 leads
Phi-4: 37.2 (#237), Qwen2.5 Plus 1127: 41.9 (#201)
| Benchmark | Phi-4 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Non-English | 1197 | 1265 |
| LMArena Chinese | 1212 | 1314 |
| LMArena German | 1222 | 1231 |
| LMArena Japanese | 1158 | 1207 |
| LMArena Russian | 1209 | 1271 |
| LMArena French | 1224 | — |
| LMArena Korean | 1151 | — |
| LMArena Spanish | 1234 | — |
Instruction Following Qwen2.5 Plus 1127 leads
Phi-4: 60.4 (#251), Qwen2.5 Plus 1127: 67.2 (#199)
| Benchmark | Phi-4 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Instruction Following | 1201 | 1275 |
| LiveBench Instruction Following | 58.4% | — |
Long Context Qwen2.5 Plus 1127 leads
Phi-4: 36.9 (#226), Qwen2.5 Plus 1127: 39.2 (#184)
| Benchmark | Phi-4 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Longer Query | 1217 | 1292 |
Writing & Preference Qwen2.5 Plus 1127 leads
Phi-4: 40.5 (#244), Qwen2.5 Plus 1127: 49.4 (#192)
| Benchmark | Phi-4 | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Text | 1217 | 1299 |
| LMArena Creative Writing | 1182 | 1262 |
| LMArena Multi-Turn | 1206 | 1299 |
| Short-Story Creative Writing | 62.6% | — |
| LiveBench Language | 25.6% | — |
Frequently asked questions
Is Phi-4 better than Qwen2.5 Plus 1127?
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.8 to 31.2 on the Noometry Index.
Is Phi-4 or Qwen2.5 Plus 1127 better for coding?
Qwen2.5 Plus 1127 scores higher on coding benchmarks: 38.5 versus 34.4 in the Noometry coding category.
How many benchmarks do Phi-4 and Qwen2.5 Plus 1127 share?
14 benchmarks have published results for both models. Phi-4 has 37 scored results on Noometry and Qwen2.5 Plus 1127 has 14.