Model comparison
phi-3-medium 14B vs Qwen3-VL 235B-A22B
Qwen3-VL 235B-A22B is the stronger model overall, scoring 42.5 to 29.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- The widest gap is in knowledge, where Qwen3-VL 235B-A22B leads 39.6 to 9.1.
Side by side
| phi-3-medium 14B | Qwen3-VL 235B-A22B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.1 | 42.5 |
| Released | 2024-04-23 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 13 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-VL 235B-A22B leads
phi-3-medium 14B: 36.3 (#198), Qwen3-VL 235B-A22B: 41.8 (#103)
| Benchmark | phi-3-medium 14B | Qwen3-VL 235B-A22B |
|---|---|---|
| BigCodeBench Instruct | 37.6% | — |
| LMArena Coding | — | 1438 |
| BigCodeBench Complete | 48.7% | — |
Reasoning Not comparable
phi-3-medium 14B: —, Qwen3-VL 235B-A22B: 28.1 (#92)
| Benchmark | phi-3-medium 14B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Hard Prompts | — | 1428 |
| Adversarial NLI | 55.8% | — |
| BIG-Bench Hard | 81.4% | — |
| Epoch Capabilities Index | 121.18 | — |
| HellaSwag | 82.4% | — |
| WinoGrande | 81.5% | — |
Math Qwen3-VL 235B-A22B leads
phi-3-medium 14B: 25.2 (#249), Qwen3-VL 235B-A22B: 36.2 (#120)
| Benchmark | phi-3-medium 14B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Math | — | 1426 |
| MATH Level 5 | 17.6% | — |
Knowledge Qwen3-VL 235B-A22B leads
phi-3-medium 14B: 9.1 (#301), Qwen3-VL 235B-A22B: 39.6 (#120)
| Benchmark | phi-3-medium 14B | Qwen3-VL 235B-A22B |
|---|---|---|
| GPQA Diamond | 27.6% | — |
| LMArena Expert | — | 1440 |
| ARC (AI2) Challenge | 91.6% | — |
| MMLU | 78% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |
Multimodal Not comparable
phi-3-medium 14B: —, Qwen3-VL 235B-A22B: 39.1 (#50)
| Benchmark | phi-3-medium 14B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Vision | — | 1247 |
Multilingual Not comparable
phi-3-medium 14B: —, Qwen3-VL 235B-A22B: 52.1 (#92)
| Benchmark | phi-3-medium 14B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Non-English | — | 1405 |
| LMArena Chinese | — | 1462 |
| LMArena French | — | 1448 |
| LMArena German | — | 1424 |
| LMArena Japanese | — | 1385 |
| LMArena Korean | — | 1395 |
| LMArena Russian | — | 1409 |
| LMArena Spanish | — | 1427 |
Instruction Following Not comparable
phi-3-medium 14B: —, Qwen3-VL 235B-A22B: 74.4 (#95)
| Benchmark | phi-3-medium 14B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Instruction Following | — | 1407 |
Long Context Not comparable
phi-3-medium 14B: —, Qwen3-VL 235B-A22B: 43.4 (#93)
| Benchmark | phi-3-medium 14B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Longer Query | — | 1420 |
Writing & Preference Not comparable
phi-3-medium 14B: —, Qwen3-VL 235B-A22B: 60.4 (#94)
| Benchmark | phi-3-medium 14B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Text | — | 1420 |
| LMArena Creative Writing | — | 1367 |
| LMArena Multi-Turn | — | 1428 |
Frequently asked questions
Is phi-3-medium 14B better than Qwen3-VL 235B-A22B?
Qwen3-VL 235B-A22B is the stronger model overall, scoring 42.5 to 29.1 on the Noometry Index.
Is phi-3-medium 14B or Qwen3-VL 235B-A22B better for coding?
Qwen3-VL 235B-A22B scores higher on coding benchmarks: 41.8 versus 36.3 in the Noometry coding category.
How many benchmarks do phi-3-medium 14B and Qwen3-VL 235B-A22B share?
0 benchmarks have published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Qwen3-VL 235B-A22B has 18.