Model comparison
Phi 3 Small 8k Instruct vs Qwen2.5 72B Instruct
Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 29.3 on the Noometry Index.
Last verified . 23 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Phi 3 Small 8k 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 31.1.
Side by side
| Phi 3 Small 8k Instruct | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.3 | 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 | 32 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 72B Instruct leads
Phi 3 Small 8k Instruct: 27.9 (#318), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1101 | 1292 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| LiveBench Coding | 20.3% | — |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
Phi 3 Small 8k Instruct: —, Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Qwen2.5 72B Instruct leads
Phi 3 Small 8k Instruct: 14.8 (#323), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1100 | 1271 |
| BIG-Bench Hard | 79.1% | 79.8% |
| HellaSwag | 77% | 84.8% |
| WinoGrande | 81.5% | 82.3% |
| LiveBench Reasoning | 15.9% | — |
| DTBench | — | 62.9% |
| LiveBench Data Analysis | 30.3% | — |
| LMCA | — | 13.4% |
| Adversarial NLI | 58.1% | — |
| Epoch Capabilities Index | — | 129 |
| ForecastBench | — | 57.5 |
| LiveBench | 24% | — |
| PIQA | — | 82.6% |
Math Phi 3 Small 8k Instruct leads
Phi 3 Small 8k Instruct: 27.6 (#248), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1151 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| LiveBench Math | 17.6% | — |
| MATH Level 5 | — | 63.2% |
Knowledge Phi 3 Small 8k Instruct leads
Phi 3 Small 8k Instruct: 29.1 (#240), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1067 | 1245 |
| ARC (AI2) Challenge | 90.7% | 94.5% |
| MMLU | 75.7% | 85.3% |
| TriviaQA | 58.1% | 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 Small 8k Instruct: 28.5 (#272), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1058 | 1252 |
| LMArena Chinese | 1061 | 1272 |
| LMArena French | 1135 | 1280 |
| LMArena German | 1080 | 1234 |
| LMArena Japanese | 966 | 1180 |
| LMArena Korean | 894 | 1188 |
| LMArena Russian | 1111 | 1264 |
| LMArena Spanish | 1111 | 1256 |
Instruction Following Qwen2.5 72B Instruct leads
Phi 3 Small 8k Instruct: 51.9 (#292), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1087 | 1254 |
| LiveBench Instruction Following | 47.2% | — |
| IFEval | — | 80.6% |
Long Context Qwen2.5 72B Instruct leads
Phi 3 Small 8k Instruct: 33.0 (#267), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1088 | 1282 |
Writing & Preference Qwen2.5 72B Instruct leads
Phi 3 Small 8k Instruct: 31.1 (#284), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1110 | 1269 |
| LMArena Creative Writing | 1083 | 1221 |
| LMArena Multi-Turn | 1068 | 1272 |
| WildBench | — | 80.2% |
| LiveBench Language | 12.9% | — |
Frequently asked questions
Is Phi 3 Small 8k Instruct better than Qwen2.5 72B Instruct?
Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 29.3 on the Noometry Index.
Is Phi 3 Small 8k Instruct or Qwen2.5 72B Instruct better for coding?
Qwen2.5 72B Instruct scores higher on coding benchmarks: 33.2 versus 27.9 in the Noometry coding category.
How many benchmarks do Phi 3 Small 8k Instruct and Qwen2.5 72B Instruct share?
23 benchmarks have published results for both models. Phi 3 Small 8k Instruct has 32 scored results on Noometry and Qwen2.5 72B Instruct has 43.