Model comparison
Phi 3 Small 8k Instruct vs Qwen2-72B
Phi 3 Small 8k Instruct and Qwen2-72B score almost the same on the Noometry Index (29.3 vs 30.0), so choose on price, context window or the category you care about most.
Last verified . 18 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Phi 3 Small 8k Instruct scores higher in 1 category and Qwen2-72B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Qwen2-72B leads 61.7 to 51.9.
Side by side
| Phi 3 Small 8k Instruct | Qwen2-72B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.3 | 30.0 |
| Released | 2024-04-23 | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2-72B leads
Phi 3 Small 8k Instruct: 27.9 (#318), Qwen2-72B: 29.1 (#310)
| Benchmark | Phi 3 Small 8k Instruct | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1101 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| LiveBench Coding | 20.3% | — |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Phi 3 Small 8k Instruct: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Phi 3 Small 8k Instruct | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Phi 3 Small 8k Instruct: 14.8 (#323), Qwen2-72B: 23.2 (#181)
| Benchmark | Phi 3 Small 8k Instruct | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1100 | 1191 |
| LiveBench Reasoning | 15.9% | — |
| LiveBench Data Analysis | 30.3% | — |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 79.1% | — |
| Epoch Capabilities Index | — | 125.28 |
| HellaSwag | 77% | — |
| LiveBench | 24% | — |
| WinoGrande | 81.5% | — |
Math Qwen2-72B leads
Phi 3 Small 8k Instruct: 27.6 (#248), Qwen2-72B: 30.2 (#236)
| Benchmark | Phi 3 Small 8k Instruct | Qwen2-72B |
|---|---|---|
| LMArena Math | 1151 | 1235 |
| LiveBench Math | 17.6% | — |
| MATH Level 5 | — | 39.1% |
Knowledge Phi 3 Small 8k Instruct leads
Phi 3 Small 8k Instruct: 29.1 (#240), Qwen2-72B: 21.2 (#275)
| Benchmark | Phi 3 Small 8k Instruct | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1067 | 1171 |
| MMLU | 75.7% | 82.4% |
| GPQA Diamond | — | 40.8% |
| ARC (AI2) Challenge | 90.7% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 58.1% | — |
Multilingual Qwen2-72B leads
Phi 3 Small 8k Instruct: 28.5 (#272), Qwen2-72B: 35.9 (#244)
| Benchmark | Phi 3 Small 8k Instruct | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1058 | 1176 |
| LMArena Chinese | 1061 | 1240 |
| LMArena French | 1135 | 1170 |
| LMArena German | 1080 | 1151 |
| LMArena Japanese | 966 | 1111 |
| LMArena Korean | 894 | 1083 |
| LMArena Russian | 1111 | 1169 |
| LMArena Spanish | 1111 | 1169 |
Instruction Following Qwen2-72B leads
Phi 3 Small 8k Instruct: 51.9 (#292), Qwen2-72B: 61.7 (#241)
| Benchmark | Phi 3 Small 8k Instruct | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1087 | 1181 |
| LiveBench Instruction Following | 47.2% | — |
Long Context Qwen2-72B leads
Phi 3 Small 8k Instruct: 33.0 (#267), Qwen2-72B: 36.1 (#235)
| Benchmark | Phi 3 Small 8k Instruct | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1088 | 1192 |
Writing & Preference Qwen2-72B leads
Phi 3 Small 8k Instruct: 31.1 (#284), Qwen2-72B: 40.8 (#241)
| Benchmark | Phi 3 Small 8k Instruct | Qwen2-72B |
|---|---|---|
| LMArena Text | 1110 | 1203 |
| LMArena Creative Writing | 1083 | 1181 |
| LMArena Multi-Turn | 1068 | 1196 |
| LiveBench Language | 12.9% | — |
Frequently asked questions
Is Phi 3 Small 8k Instruct better than Qwen2-72B?
Phi 3 Small 8k Instruct and Qwen2-72B score almost the same on the Noometry Index (29.3 vs 30.0), so choose on price, context window or the category you care about most.
Is Phi 3 Small 8k Instruct or Qwen2-72B better for coding?
Qwen2-72B scores higher on coding benchmarks: 29.1 versus 27.9 in the Noometry coding category.
How many benchmarks do Phi 3 Small 8k Instruct and Qwen2-72B share?
18 benchmarks have published results for both models. Phi 3 Small 8k Instruct has 32 scored results on Noometry and Qwen2-72B has 26.