Model comparison
Phi 3 Medium 4k Instruct vs Qwen1.5-72B
Phi 3 Medium 4k Instruct is the stronger model overall, scoring 33.0 to 30.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Phi 3 Medium 4k Instruct scores higher in 3 categories and Qwen1.5-72B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi 3 Medium 4k Instruct leads 30.2 to 11.5.
Side by side
| Phi 3 Medium 4k Instruct | Qwen1.5-72B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 33.0 | 30.8 |
| Released | — | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Phi 3 Medium 4k Instruct: 32.9 (#268), Qwen1.5-72B: 31.9 (#277)
| Benchmark | Phi 3 Medium 4k Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1130 | 1165 |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Reasoning Too close to call
Phi 3 Medium 4k Instruct: 21.7 (#214), Qwen1.5-72B: 22.2 (#203)
| Benchmark | Phi 3 Medium 4k Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1127 | 1148 |
Math Too close to call
Phi 3 Medium 4k Instruct: 33.4 (#202), Qwen1.5-72B: 33.2 (#205)
| Benchmark | Phi 3 Medium 4k Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1173 | 1164 |
Knowledge Phi 3 Medium 4k Instruct leads
Phi 3 Medium 4k Instruct: 30.2 (#229), Qwen1.5-72B: 11.5 (#300)
| Benchmark | Phi 3 Medium 4k Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1108 | 1136 |
| GPQA Diamond | — | 28.8% |
Multilingual Qwen1.5-72B leads
Phi 3 Medium 4k Instruct: 30.6 (#263), Qwen1.5-72B: 33.2 (#253)
| Benchmark | Phi 3 Medium 4k Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1094 | 1135 |
| LMArena Chinese | 1108 | 1186 |
| LMArena French | 1110 | 1159 |
| LMArena German | 1101 | 1084 |
| LMArena Japanese | 1042 | 1061 |
| LMArena Korean | 954 | 1050 |
| LMArena Russian | 1145 | 1104 |
| LMArena Spanish | 1095 | 1110 |
Instruction Following Qwen1.5-72B leads
Phi 3 Medium 4k Instruct: 57.6 (#268), Qwen1.5-72B: 59.3 (#256)
| Benchmark | Phi 3 Medium 4k Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1113 | 1141 |
Long Context Qwen1.5-72B leads
Phi 3 Medium 4k Instruct: 34.0 (#255), Qwen1.5-72B: 35.1 (#243)
| Benchmark | Phi 3 Medium 4k Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1120 | 1157 |
Writing & Preference Qwen1.5-72B leads
Phi 3 Medium 4k Instruct: 34.1 (#272), Qwen1.5-72B: 37.3 (#258)
| Benchmark | Phi 3 Medium 4k Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1138 | 1166 |
| LMArena Creative Writing | 1107 | 1137 |
| LMArena Multi-Turn | 1088 | 1160 |
Frequently asked questions
Is Phi 3 Medium 4k Instruct better than Qwen1.5-72B?
Phi 3 Medium 4k Instruct is the stronger model overall, scoring 33.0 to 30.8 on the Noometry Index.
Is Phi 3 Medium 4k Instruct or Qwen1.5-72B better for coding?
They score almost the same on coding (32.9 vs 31.9); test both on your own repository before choosing.
How many benchmarks do Phi 3 Medium 4k Instruct and Qwen1.5-72B share?
17 benchmarks have published results for both models. Phi 3 Medium 4k Instruct has 17 scored results on Noometry and Qwen1.5-72B has 22.