Model comparison
Phi 3 Mini 128k Instruct vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.4 to 29.1 on the Noometry Index.
Last verified . 19 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Phi 3 Mini 128k Instruct scores higher in 0 categories and QwQ-32B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where QwQ-32B leads 50.9 to 27.3.
- The biggest single-benchmark swing is BigCodeBench Instruct: 29.6% for Phi 3 Mini 128k Instruct and 44.6% for QwQ-32B.
Side by side
| Phi 3 Mini 128k Instruct | QwQ-32B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.1 | 39.4 |
| Released | 2024-04-23 | 2024-11-28 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding QwQ-32B leads
Phi 3 Mini 128k Instruct: 28.3 (#307), QwQ-32B: 34.9 (#220)
| Benchmark | Phi 3 Mini 128k Instruct | QwQ-32B |
|---|---|---|
| BigCodeBench Instruct | 29.6% | 44.6% |
| LMArena Coding | 1040 | 1333 |
| BigCodeBench Complete | 40.6% | 54.4% |
| Aider Polyglot | — | 20.9% |
| LiveBench Coding | — | 72.2% |
Reasoning QwQ-32B leads
Phi 3 Mini 128k Instruct: 18.7 (#254), QwQ-32B: 22.9 (#171)
| Benchmark | Phi 3 Mini 128k Instruct | QwQ-32B |
|---|---|---|
| LMArena Hard Prompts | 1028 | 1326 |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | — | 83.5% |
| LiveBench Data Analysis | — | 65% |
| Epoch Capabilities Index | — | 137.6 |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |
Math QwQ-32B leads
Phi 3 Mini 128k Instruct: 29.2 (#220), QwQ-32B: 36.2 (#123)
| Benchmark | Phi 3 Mini 128k Instruct | QwQ-32B |
|---|---|---|
| LMArena Math | 1089 | 1359 |
| OTIS Mock AIME 2024-2025 | — | 59.2% |
| LiveBench Math | — | 77.8% |
Knowledge QwQ-32B leads
Phi 3 Mini 128k Instruct: 26.3 (#251), QwQ-32B: 37.2 (#150)
| Benchmark | Phi 3 Mini 128k Instruct | QwQ-32B |
|---|---|---|
| LMArena Expert | 984 | 1323 |
| GPQA Diamond | — | 65.3% |
| Confabulations | — | 15.6% |
Multilingual QwQ-32B leads
Phi 3 Mini 128k Instruct: 25.4 (#280), QwQ-32B: 45.0 (#171)
| Benchmark | Phi 3 Mini 128k Instruct | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1000 | 1306 |
| LMArena Chinese | 1016 | 1378 |
| LMArena French | 1038 | 1337 |
| LMArena German | 1006 | 1313 |
| LMArena Japanese | 899 | 1263 |
| LMArena Korean | 856 | 1278 |
| LMArena Russian | 1004 | 1297 |
| LMArena Spanish | 1058 | 1353 |
Instruction Following QwQ-32B leads
Phi 3 Mini 128k Instruct: 52.1 (#289), QwQ-32B: 72.8 (#131)
| Benchmark | Phi 3 Mini 128k Instruct | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1023 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
Long Context QwQ-32B leads
Phi 3 Mini 128k Instruct: 30.3 (#284), QwQ-32B: 49.0 (#11)
| Benchmark | Phi 3 Mini 128k Instruct | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 996 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference QwQ-32B leads
Phi 3 Mini 128k Instruct: 27.3 (#296), QwQ-32B: 50.9 (#175)
| Benchmark | Phi 3 Mini 128k Instruct | QwQ-32B |
|---|---|---|
| LMArena Text | 1050 | 1329 |
| LMArena Creative Writing | 1024 | 1288 |
| LMArena Multi-Turn | 989 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is Phi 3 Mini 128k Instruct better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.4 to 29.1 on the Noometry Index.
Is Phi 3 Mini 128k Instruct or QwQ-32B better for coding?
QwQ-32B scores higher on coding benchmarks: 34.9 versus 28.3 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 128k Instruct and QwQ-32B share?
19 benchmarks have published results for both models. Phi 3 Mini 128k Instruct has 19 scored results on Noometry and QwQ-32B has 36.