Model comparison
Phi 3 Mini 4k Instruct June 2024 vs Qwen3.5 27B
Qwen3.5 27B is the stronger model overall, scoring 41.9 to 31.3 on the Noometry Index.
Last verified . 15 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 15 benchmarks with published results for both. Phi 3 Mini 4k Instruct June 2024 scores higher in 0 categories and Qwen3.5 27B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 27B leads 59.3 to 29.6.
Side by side
| Phi 3 Mini 4k Instruct June 2024 | Qwen3.5 27B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 31.3 | 41.9 |
| Released | — | 2026-02-23 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.40 |
| Results tracked | 15 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 27B leads
Phi 3 Mini 4k Instruct June 2024: 31.8 (#279), Qwen3.5 27B: 38.9 (#168)
| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen3.5 27B |
|---|---|---|
| LMArena Coding | 1093 | 1427 |
| LMArena WebDev | — | 1358 |
| WeirdML | — | 39.5% |
| ALE-Bench | — | 349.45 |
Agentic & Tool Use Not comparable
Phi 3 Mini 4k Instruct June 2024: —, Qwen3.5 27B: —
| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen3.5 27B |
|---|---|---|
| Vending-Bench 2 | — | 201.98 |
Reasoning Qwen3.5 27B leads
Phi 3 Mini 4k Instruct June 2024: 20.8 (#231), Qwen3.5 27B: 27.5 (#117)
| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen3.5 27B |
|---|---|---|
| LMArena Hard Prompts | 1087 | 1414 |
| NYT Connections (extended) | — | 47.9% |
| Thematic Generalization | — | 45.5% |
| DTBench | — | 82.4% |
| LMCA | — | 34% |
Math Qwen3.5 27B leads
Phi 3 Mini 4k Instruct June 2024: 33.0 (#208), Qwen3.5 27B: 38.8 (#127)
| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen3.5 27B |
|---|---|---|
| LMArena Math | 1152 | 1429 |
| MathArena Final-Answer Competitions | — | 56.7% |
Knowledge Qwen3.5 27B leads
Phi 3 Mini 4k Instruct June 2024: 28.6 (#244), Qwen3.5 27B: 38.0 (#150)
| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen3.5 27B |
|---|---|---|
| LMArena Expert | 1051 | 1428 |
| Vectara Hallucination Rate | — | 12.1% |
Multimodal Not comparable
Phi 3 Mini 4k Instruct June 2024: —, Qwen3.5 27B: 39.4 (#59)
| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen3.5 27B |
|---|---|---|
| LMArena Vision | — | 1241 |
Multilingual Qwen3.5 27B leads
Phi 3 Mini 4k Instruct June 2024: 25.9 (#282), Qwen3.5 27B: 50.8 (#115)
| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen3.5 27B |
|---|---|---|
| LMArena Non-English | 1013 | 1390 |
| LMArena Chinese | 1033 | 1478 |
| LMArena German | 1031 | 1393 |
| LMArena Japanese | 954 | 1345 |
| LMArena Korean | 880 | 1358 |
| LMArena Russian | 1019 | 1390 |
| LMArena French | — | 1410 |
| LMArena Spanish | — | 1407 |
Instruction Following Qwen3.5 27B leads
Phi 3 Mini 4k Instruct June 2024: 54.1 (#282), Qwen3.5 27B: 73.5 (#119)
| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen3.5 27B |
|---|---|---|
| LMArena Instruction Following | 1058 | 1393 |
Long Context Qwen3.5 27B leads
Phi 3 Mini 4k Instruct June 2024: 31.7 (#277), Qwen3.5 27B: 43.1 (#106)
| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen3.5 27B |
|---|---|---|
| LMArena Longer Query | 1042 | 1413 |
Writing & Preference Qwen3.5 27B leads
Phi 3 Mini 4k Instruct June 2024: 29.6 (#294), Qwen3.5 27B: 59.3 (#111)
| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen3.5 27B |
|---|---|---|
| LMArena Text | 1080 | 1409 |
| LMArena Creative Writing | 1045 | 1362 |
| LMArena Multi-Turn | 1049 | 1410 |
Frequently asked questions
Is Phi 3 Mini 4k Instruct June 2024 better than Qwen3.5 27B?
Qwen3.5 27B is the stronger model overall, scoring 41.9 to 31.3 on the Noometry Index.
Is Phi 3 Mini 4k Instruct June 2024 or Qwen3.5 27B better for coding?
Qwen3.5 27B scores higher on coding benchmarks: 38.9 versus 31.8 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 4k Instruct June 2024 and Qwen3.5 27B share?
15 benchmarks have published results for both models. Phi 3 Mini 4k Instruct June 2024 has 15 scored results on Noometry and Qwen3.5 27B has 28.