Model comparison
Phi 3 Mini 128k Instruct vs Qwen-14B
Qwen-14B is the stronger model overall, scoring 31.4 to 29.7 on the Noometry Index.
Last verified . 10 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Phi 3 Mini 128k Instruct scores higher in 2 categories and Qwen-14B in 5 categories; 2 gaps are clear of the uncertainty.
Side by side
| Phi 3 Mini 128k Instruct | Qwen-14B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.7 | 31.4 |
| Released | 2024-04-23 | 2023-09-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen-14B leads
Phi 3 Mini 128k Instruct: 28.8 (#312), Qwen-14B: 31.2 (#288)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen-14B |
|---|---|---|
| LMArena Coding | 1039 | 1071 |
| BigCodeBench Instruct | 29.6% | — |
| BigCodeBench Complete | 40.6% | — |
Reasoning Too close to call
Phi 3 Mini 128k Instruct: 19.6 (#256), Qwen-14B: 19.6 (#257)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1028 | 1027 |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 113.03 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Too close to call
Phi 3 Mini 128k Instruct: 31.6 (#222), Qwen-14B: 31.2 (#227)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen-14B |
|---|---|---|
| LMArena Math | 1089 | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Phi 3 Mini 128k Instruct: 26.8 (#254), Qwen-14B: —
| Benchmark | Phi 3 Mini 128k Instruct | Qwen-14B |
|---|---|---|
| LMArena Expert | 984 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Qwen-14B leads
Phi 3 Mini 128k Instruct: 25.2 (#285), Qwen-14B: 27.5 (#275)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1000 | 1041 |
| LMArena Chinese | 1016 | 1077 |
| LMArena French | 1039 | — |
| LMArena German | 1006 | — |
| LMArena Japanese | 899 | — |
| LMArena Korean | 856 | — |
| LMArena Russian | 1004 | — |
| LMArena Spanish | 1059 | — |
Instruction Following Too close to call
Phi 3 Mini 128k Instruct: 51.8 (#294), Qwen-14B: 52.4 (#289)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1023 | 1031 |
Long Context Too close to call
Phi 3 Mini 128k Instruct: 30.4 (#289), Qwen-14B: 31.3 (#280)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 996 | 1028 |
Writing & Preference Too close to call
Phi 3 Mini 128k Instruct: 27.1 (#301), Qwen-14B: 27.6 (#299)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen-14B |
|---|---|---|
| LMArena Text | 1050 | 1051 |
| LMArena Creative Writing | 1024 | 1028 |
| LMArena Multi-Turn | 989 | 1022 |
Frequently asked questions
Is Phi 3 Mini 128k Instruct better than Qwen-14B?
Qwen-14B is the stronger model overall, scoring 31.4 to 29.7 on the Noometry Index.
Is Phi 3 Mini 128k Instruct or Qwen-14B better for coding?
Qwen-14B scores higher on coding benchmarks: 31.2 versus 28.8 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 128k Instruct and Qwen-14B share?
10 benchmarks have published results for both models. Phi 3 Mini 128k Instruct has 19 scored results on Noometry and Qwen-14B has 18.