Model comparison
Qwen2-72B vs Qwen3-VL 235B-A22B
Qwen3-VL 235B-A22B is the stronger model overall, scoring 43.2 to 30.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Qwen2-72B scores higher in 0 categories and Qwen3-VL 235B-A22B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3-VL 235B-A22B leads 60.2 to 40.8.
Side by side
| Qwen2-72B | Qwen3-VL 235B-A22B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.0 | 43.2 |
| Released | 2024-06-07 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 26 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-VL 235B-A22B leads
Qwen2-72B: 29.1 (#310), Qwen3-VL 235B-A22B: 42.4 (#100)
| Benchmark | Qwen2-72B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Coding | 1196 | 1439 |
| WeirdML | 11.3% | — |
| BigCodeBench Instruct | 38.5% | — |
| BigCodeBench Complete | 54% | — |
Agentic & Tool Use Not comparable
Qwen2-72B: 17.0 (#146), Qwen3-VL 235B-A22B: —
| Benchmark | Qwen2-72B | Qwen3-VL 235B-A22B |
|---|---|---|
| TheAgentCompany | 1.1% | — |
| METR Time Horizons | 29.9% | — |
Reasoning Qwen3-VL 235B-A22B leads
Qwen2-72B: 23.2 (#181), Qwen3-VL 235B-A22B: 29.3 (#92)
| Benchmark | Qwen2-72B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1428 |
| Epoch Capabilities Index | 125.28 | — |
Math Qwen3-VL 235B-A22B leads
Qwen2-72B: 30.2 (#236), Qwen3-VL 235B-A22B: 39.0 (#118)
| Benchmark | Qwen2-72B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Math | 1235 | 1426 |
| MATH Level 5 | 39.1% | — |
Knowledge Qwen3-VL 235B-A22B leads
Qwen2-72B: 21.2 (#275), Qwen3-VL 235B-A22B: 40.3 (#121)
| Benchmark | Qwen2-72B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Expert | 1171 | 1442 |
| GPQA Diamond | 40.8% | — |
| MMLU | 82.4% | — |
Multimodal Not comparable
Qwen2-72B: —, Qwen3-VL 235B-A22B: 39.8 (#55)
| Benchmark | Qwen2-72B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Vision | — | 1247 |
Multilingual Qwen3-VL 235B-A22B leads
Qwen2-72B: 35.9 (#244), Qwen3-VL 235B-A22B: 51.9 (#97)
| Benchmark | Qwen2-72B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Non-English | 1176 | 1405 |
| LMArena Chinese | 1240 | 1463 |
| LMArena French | 1170 | 1452 |
| LMArena German | 1151 | 1424 |
| LMArena Japanese | 1111 | 1385 |
| LMArena Korean | 1083 | 1394 |
| LMArena Russian | 1169 | 1408 |
| LMArena Spanish | 1169 | 1428 |
Instruction Following Qwen3-VL 235B-A22B leads
Qwen2-72B: 61.7 (#241), Qwen3-VL 235B-A22B: 74.2 (#101)
| Benchmark | Qwen2-72B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1181 | 1406 |
Long Context Qwen3-VL 235B-A22B leads
Qwen2-72B: 36.1 (#235), Qwen3-VL 235B-A22B: 43.4 (#98)
| Benchmark | Qwen2-72B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1192 | 1420 |
Writing & Preference Qwen3-VL 235B-A22B leads
Qwen2-72B: 40.8 (#241), Qwen3-VL 235B-A22B: 60.2 (#99)
| Benchmark | Qwen2-72B | Qwen3-VL 235B-A22B |
|---|---|---|
| LMArena Text | 1203 | 1420 |
| LMArena Creative Writing | 1181 | 1366 |
| LMArena Multi-Turn | 1196 | 1428 |
Frequently asked questions
Is Qwen2-72B better than Qwen3-VL 235B-A22B?
Qwen3-VL 235B-A22B is the stronger model overall, scoring 43.2 to 30.0 on the Noometry Index.
Is Qwen2-72B or Qwen3-VL 235B-A22B better for coding?
Qwen3-VL 235B-A22B scores higher on coding benchmarks: 42.4 versus 29.1 in the Noometry coding category.
How many benchmarks do Qwen2-72B and Qwen3-VL 235B-A22B share?
17 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Qwen3-VL 235B-A22B has 18.