Model comparison
Phi 3 Small 8k Instruct vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 29.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Phi 3 Small 8k Instruct scores higher in 0 categories and Qwen3.5 397B-A17B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 397B-A17B leads 62.3 to 31.1.
Side by side
| Phi 3 Small 8k Instruct | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.3 | 46.0 |
| Released | 2024-04-23 | 2026-02-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $3.60 |
| Results tracked | 32 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 397B-A17B leads
Phi 3 Small 8k Instruct: 27.9 (#318), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | Phi 3 Small 8k Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Coding | 1101 | 1465 |
| LMArena WebDev | — | 1400 |
| LiveBench Coding | 20.3% | — |
Agentic & Tool Use Not comparable
Phi 3 Small 8k Instruct: —, Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | Phi 3 Small 8k Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
Reasoning Qwen3.5 397B-A17B leads
Phi 3 Small 8k Instruct: 14.8 (#323), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | Phi 3 Small 8k Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Hard Prompts | 1100 | 1448 |
| Kagi LLM Benchmark | — | 73.7% |
| NYT Connections (extended) | — | 58.9% |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| LiveBench Reasoning | 15.9% | — |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 87.5% |
| LiveBench Data Analysis | 30.3% | — |
| LMCA | — | 37.9% |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 79.1% | — |
| Epoch Capabilities Index | — | 146.65 |
| HellaSwag | 77% | — |
| LiveBench | 24% | — |
| WinoGrande | 81.5% | — |
Math Qwen3.5 397B-A17B leads
Phi 3 Small 8k Instruct: 27.6 (#248), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | Phi 3 Small 8k Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Math | 1151 | 1454 |
| FrontierMath (Tiers 1-3) | — | 31.2% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| LiveBench Math | 17.6% | — |
Knowledge Qwen3.5 397B-A17B leads
Phi 3 Small 8k Instruct: 29.1 (#240), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | Phi 3 Small 8k Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Expert | 1067 | 1462 |
| GPQA Diamond | — | 86.4% |
| ARC (AI2) Challenge | 90.7% | — |
| MMLU | 75.7% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 58.1% | — |
Multimodal Not comparable
Phi 3 Small 8k Instruct: —, Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | Phi 3 Small 8k Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1263 |
Multilingual Qwen3.5 397B-A17B leads
Phi 3 Small 8k Instruct: 28.5 (#272), Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | Phi 3 Small 8k Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1058 | 1430 |
| LMArena Chinese | 1061 | 1500 |
| LMArena French | 1135 | 1461 |
| LMArena German | 1080 | 1447 |
| LMArena Japanese | 966 | 1426 |
| LMArena Korean | 894 | 1384 |
| LMArena Russian | 1111 | 1429 |
| LMArena Spanish | 1111 | 1441 |
Instruction Following Qwen3.5 397B-A17B leads
Phi 3 Small 8k Instruct: 51.9 (#292), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | Phi 3 Small 8k Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1087 | 1424 |
| LiveBench Instruction Following | 47.2% | — |
Long Context Qwen3.5 397B-A17B leads
Phi 3 Small 8k Instruct: 33.0 (#267), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | Phi 3 Small 8k Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1088 | 1442 |
Writing & Preference Qwen3.5 397B-A17B leads
Phi 3 Small 8k Instruct: 31.1 (#284), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | Phi 3 Small 8k Instruct | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1110 | 1438 |
| LMArena Creative Writing | 1083 | 1401 |
| LMArena Multi-Turn | 1068 | 1446 |
| EQ-Bench Creative Writing | — | 1478 |
| LiveBench Language | 12.9% | — |
Frequently asked questions
Is Phi 3 Small 8k Instruct better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 29.3 on the Noometry Index.
Is Phi 3 Small 8k Instruct or Qwen3.5 397B-A17B better for coding?
Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 27.9 in the Noometry coding category.
How many benchmarks do Phi 3 Small 8k Instruct and Qwen3.5 397B-A17B share?
17 benchmarks have published results for both models. Phi 3 Small 8k Instruct has 32 scored results on Noometry and Qwen3.5 397B-A17B has 36.