Model comparison
Qwen2-72B vs Qwen3 14B
Qwen3 14B is the stronger model overall, scoring 35.0 to 29.5 on the Noometry Index.
Last verified . 2 shared benchmarks.
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. Qwen2-72B scores higher in 1 category and Qwen3 14B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 14B leads 39.2 to 21.2.
- The biggest single-benchmark swing is GPQA Diamond: 40.8% for Qwen2-72B and 63.8% for Qwen3 14B.
Side by side
| Qwen2-72B | Qwen3 14B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 29.5 | 35.0 |
| Released | 2024-06-07 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.35 |
| Output $ / M tokens | — | $1.40 |
| Results tracked | 26 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 14B leads
Qwen2-72B: 28.7 (#303), Qwen3 14B: 36.7 (#191)
| Benchmark | Qwen2-72B | Qwen3 14B |
|---|---|---|
| SciCode | — | 31.6% |
| WeirdML | 11.3% | — |
| BigCodeBench Instruct | 38.5% | — |
| LMArena Coding | 1196 | — |
| BigCodeBench Complete | 54% | — |
Agentic & Tool Use Qwen3 14B leads
Qwen2-72B: 16.9 (#138), Qwen3 14B: 29.4 (#78)
| Benchmark | Qwen2-72B | Qwen3 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41% |
| TheAgentCompany | 1.1% | — |
| METR Time Horizons | 29.9% | — |
Reasoning Qwen2-72B leads
Qwen2-72B: 22.2 (#184), Qwen3 14B: 18.1 (#272)
| Benchmark | Qwen2-72B | Qwen3 14B |
|---|---|---|
| Epoch Capabilities Index | 125.27 | 138.23 |
| Kagi LLM Benchmark | — | 49.1% |
| CritPt | — | 0% |
| Chess Puzzles | — | 4% |
| LMArena Hard Prompts | 1191 | — |
| DTBench | — | 64% |
| LMCA | — | 18.2% |
Math Qwen3 14B leads
Qwen2-72B: 27.9 (#232), Qwen3 14B: 37.0 (#102)
| Benchmark | Qwen2-72B | Qwen3 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 66.4% |
| LMArena Math | 1235 | — |
| MATH Level 5 | 39.1% | — |
Knowledge Qwen3 14B leads
Qwen2-72B: 21.2 (#270), Qwen3 14B: 39.2 (#124)
| Benchmark | Qwen2-72B | Qwen3 14B |
|---|---|---|
| GPQA Diamond | 40.8% | 63.8% |
| Vectara Hallucination Rate | — | 5.4% |
| LMArena Expert | 1171 | — |
| MMLU | 82.4% | — |
Multilingual Not comparable
Qwen2-72B: 36.0 (#239), Qwen3 14B: —
| Benchmark | Qwen2-72B | Qwen3 14B |
|---|---|---|
| LMArena Non-English | 1176 | — |
| LMArena Chinese | 1240 | — |
| LMArena French | 1169 | — |
| LMArena German | 1151 | — |
| LMArena Japanese | 1111 | — |
| LMArena Korean | 1083 | — |
| LMArena Russian | 1169 | — |
| LMArena Spanish | 1168 | — |
Instruction Following Not comparable
Qwen2-72B: 62.0 (#236), Qwen3 14B: —
| Benchmark | Qwen2-72B | Qwen3 14B |
|---|---|---|
| LMArena Instruction Following | 1181 | — |
Long Context Qwen3 14B leads
Qwen2-72B: 36.1 (#230), Qwen3 14B: 38.0 (#201)
| Benchmark | Qwen2-72B | Qwen3 14B |
|---|---|---|
| Fiction.LiveBench | — | 62.5% |
| LMArena Longer Query | 1193 | — |
Writing & Preference Not comparable
Qwen2-72B: 41.0 (#236), Qwen3 14B: —
| Benchmark | Qwen2-72B | Qwen3 14B |
|---|---|---|
| LMArena Text | 1203 | — |
| LMArena Creative Writing | 1181 | — |
| LMArena Multi-Turn | 1195 | — |
Frequently asked questions
Is Qwen2-72B better than Qwen3 14B?
Qwen3 14B is the stronger model overall, scoring 35.0 to 29.5 on the Noometry Index.
Is Qwen2-72B or Qwen3 14B better for coding?
Qwen3 14B scores higher on coding benchmarks: 36.7 versus 28.7 in the Noometry coding category.
How many benchmarks do Qwen2-72B and Qwen3 14B share?
2 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Qwen3 14B has 12.