Model comparison
Phi 3 Mini 128k Instruct vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 39.2 to 29.7 on the Noometry Index.
Last verified . 13 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Phi 3 Mini 128k Instruct scores higher in 0 categories and Qwen3 32B in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3 32B leads 52.9 to 27.1.
Side by side
| Phi 3 Mini 128k Instruct | Qwen3 32B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.7 | 39.2 |
| Released | 2024-04-23 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 19 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
Phi 3 Mini 128k Instruct: 28.8 (#312), Qwen3 32B: 37.7 (#190)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen3 32B |
|---|---|---|
| LMArena Coding | 1039 | 1358 |
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
| BigCodeBench Instruct | 29.6% | — |
| BigCodeBench Complete | 40.6% | — |
Agentic & Tool Use Not comparable
Phi 3 Mini 128k Instruct: —, Qwen3 32B: 32.6 (#62)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning Too close to call
Phi 3 Mini 128k Instruct: 19.6 (#256), Qwen3 32B: 20.2 (#241)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen3 32B |
|---|---|---|
| LMArena Hard Prompts | 1028 | 1334 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| Epoch Capabilities Index | — | 138.51 |
Math Qwen3 32B leads
Phi 3 Mini 128k Instruct: 31.6 (#222), Qwen3 32B: 39.7 (#99)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen3 32B |
|---|---|---|
| LMArena Math | 1089 | 1399 |
| OTIS Mock AIME 2024-2025 | — | 66.9% |
Knowledge Qwen3 32B leads
Phi 3 Mini 128k Instruct: 26.8 (#254), Qwen3 32B: 40.0 (#125)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen3 32B |
|---|---|---|
| LMArena Expert | 984 | 1362 |
| GPQA Diamond | — | 65.7% |
| Vectara Hallucination Rate | — | 5.9% |
Multilingual Qwen3 32B leads
Phi 3 Mini 128k Instruct: 25.2 (#285), Qwen3 32B: 45.6 (#167)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1000 | 1317 |
| LMArena Chinese | 1016 | 1357 |
| LMArena German | 1006 | 1341 |
| LMArena Russian | 1004 | 1311 |
| LMArena French | 1039 | — |
| LMArena Japanese | 899 | — |
| LMArena Korean | 856 | — |
| LMArena Spanish | 1059 | — |
Instruction Following Qwen3 32B leads
Phi 3 Mini 128k Instruct: 51.8 (#294), Qwen3 32B: 68.9 (#179)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1023 | 1305 |
Long Context Qwen3 32B leads
Phi 3 Mini 128k Instruct: 30.4 (#289), Qwen3 32B: 43.8 (#87)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 996 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference Qwen3 32B leads
Phi 3 Mini 128k Instruct: 27.1 (#301), Qwen3 32B: 52.9 (#163)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen3 32B |
|---|---|---|
| LMArena Text | 1050 | 1340 |
| LMArena Creative Writing | 1024 | 1297 |
| LMArena Multi-Turn | 989 | 1331 |
Frequently asked questions
Is Phi 3 Mini 128k Instruct better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 39.2 to 29.7 on the Noometry Index.
Is Phi 3 Mini 128k Instruct or Qwen3 32B better for coding?
Qwen3 32B scores higher on coding benchmarks: 37.7 versus 28.8 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 128k Instruct and Qwen3 32B share?
13 benchmarks have published results for both models. Phi 3 Mini 128k Instruct has 19 scored results on Noometry and Qwen3 32B has 26.