Model comparison
Phi 3 Mini 4k Instruct vs Qwen2.5 72B Instruct
Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 27.9 on the Noometry Index.
Last verified . 23 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 2 categories and Qwen2.5 72B Instruct in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 72B Instruct leads 46.7 to 27.6.
Side by side
| Phi 3 Mini 4k Instruct | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 27.9 | 31.9 |
| Released | 2024-04-23 | 2024-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.40 |
| Output $ / M tokens | — | $5.60 |
| Results tracked | 35 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 72B Instruct leads
Phi 3 Mini 4k Instruct: 26.6 (#323), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1093 | 1292 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| LiveBench Coding | 15.5% | — |
| BigCodeBench Complete | — | 55.9% |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |
Agentic & Tool Use Not comparable
Phi 3 Mini 4k Instruct: —, Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Qwen2.5 72B Instruct leads
Phi 3 Mini 4k Instruct: 14.1 (#328), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1072 | 1271 |
| BIG-Bench Hard | 71.7% | 79.8% |
| HellaSwag | 76.7% | 84.8% |
| WinoGrande | 70.8% | 82.3% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 26.8% | — |
| DTBench | — | 62.9% |
| LiveBench Data Analysis | 34.7% | — |
| LMCA | — | 13.4% |
| Adversarial NLI | 52.8% | — |
| Epoch Capabilities Index | — | 129 |
| ForecastBench | — | 57.5 |
| LiveBench | 22.4% | — |
| PIQA | — | 82.6% |
Math Phi 3 Mini 4k Instruct leads
Phi 3 Mini 4k Instruct: 26.6 (#257), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1111 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| LiveBench Math | 15.7% | — |
| MATH Level 5 | — | 63.2% |
Knowledge Phi 3 Mini 4k Instruct leads
Phi 3 Mini 4k Instruct: 28.5 (#246), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1045 | 1245 |
| ARC (AI2) Challenge | 84.9% | 94.5% |
| MMLU | 68.8% | 85.3% |
| TriviaQA | 64% | 71.9% |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| OpenBookQA | 88% | — |
Multilingual Qwen2.5 72B Instruct leads
Phi 3 Mini 4k Instruct: 26.3 (#280), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1021 | 1252 |
| LMArena Chinese | 1021 | 1272 |
| LMArena French | 1076 | 1280 |
| LMArena German | 1044 | 1234 |
| LMArena Japanese | 935 | 1180 |
| LMArena Korean | 905 | 1188 |
| LMArena Russian | 1022 | 1264 |
| LMArena Spanish | 1085 | 1256 |
Instruction Following Qwen2.5 72B Instruct leads
Phi 3 Mini 4k Instruct: 47.7 (#303), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1053 | 1254 |
| LiveBench Instruction Following | 39.1% | — |
| IFEval | — | 80.6% |
Long Context Qwen2.5 72B Instruct leads
Phi 3 Mini 4k Instruct: 31.7 (#276), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1044 | 1282 |
Writing & Preference Qwen2.5 72B Instruct leads
Phi 3 Mini 4k Instruct: 27.6 (#300), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1073 | 1269 |
| LMArena Creative Writing | 1037 | 1221 |
| LMArena Multi-Turn | 1018 | 1272 |
| WildBench | — | 80.2% |
| LiveBench Language | 9.2% | — |
Frequently asked questions
Is Phi 3 Mini 4k Instruct better than Qwen2.5 72B Instruct?
Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 27.9 on the Noometry Index.
Is Phi 3 Mini 4k Instruct or Qwen2.5 72B Instruct better for coding?
Qwen2.5 72B Instruct scores higher on coding benchmarks: 33.2 versus 26.6 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 4k Instruct and Qwen2.5 72B Instruct share?
23 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Qwen2.5 72B Instruct has 43.