Model comparison
Qwen-14B vs Qwen3-30B-A3B
Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 30.8 on the Noometry Index.
Last verified . 11 shared benchmarks.
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Qwen-14B scores higher in 1 category and Qwen3-30B-A3B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3-30B-A3B leads 55.9 to 27.8.
Side by side
| Qwen-14B | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.8 | 38.5 |
| Released | 2023-09-24 | 2025-04-28 |
| Weights | Open | Open |
| Context window | — | 41K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.12 |
| Output $ / M tokens | — | $0.50 |
| Results tracked | 18 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-30B-A3B leads
Qwen-14B: 30.6 (#283), Qwen3-30B-A3B: 37.0 (#188)
| Benchmark | Qwen-14B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Coding | 1072 | 1416 |
| SciCode | — | 33.3% |
| WeirdML | — | 29.8% |
Agentic & Tool Use Not comparable
Qwen-14B: —, Qwen3-30B-A3B: 29.5 (#75)
| Benchmark | Qwen-14B | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |
Reasoning Qwen3-30B-A3B leads
Qwen-14B: 18.7 (#255), Qwen3-30B-A3B: 21.6 (#193)
| Benchmark | Qwen-14B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1027 | 1398 |
| Epoch Capabilities Index | 112.8 | 139.63 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 8% |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
| BIG-Bench Hard | 55% | — |
| LAMBADA | 71.1% | — |
| PIQA | 79.9% | — |
Math Qwen3-30B-A3B leads
Qwen-14B: 28.7 (#224), Qwen3-30B-A3B: 36.0 (#133)
| Benchmark | Qwen-14B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 1068 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
| GSM8K | 61.3% | — |
Knowledge Not comparable
Qwen-14B: —, Qwen3-30B-A3B: 41.7 (#96)
| Benchmark | Qwen-14B | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | — | 70.1% |
| Confabulations | — | 12.3% |
| LMArena Expert | — | 1395 |
| ARC (AI2) Challenge | 84.4% | — |
| BoolQ | 86.2% | — |
| MMLU | 66.3% | — |
Multilingual Qwen3-30B-A3B leads
Qwen-14B: 27.7 (#270), Qwen3-30B-A3B: 49.8 (#126)
| Benchmark | Qwen-14B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1042 | 1372 |
| LMArena Chinese | 1077 | 1434 |
| LMArena French | — | 1419 |
| LMArena German | — | 1379 |
| LMArena Japanese | — | 1338 |
| LMArena Korean | — | 1333 |
| LMArena Russian | — | 1369 |
| LMArena Spanish | — | 1403 |
Instruction Following Qwen3-30B-A3B leads
Qwen-14B: 52.6 (#284), Qwen3-30B-A3B: 72.2 (#137)
| Benchmark | Qwen-14B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1031 | 1364 |
Long Context Too close to call
Qwen-14B: 31.3 (#276), Qwen3-30B-A3B: 31.0 (#278)
| Benchmark | Qwen-14B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1029 | 1379 |
| Fiction.LiveBench | — | 40.6% |
Writing & Preference Qwen3-30B-A3B leads
Qwen-14B: 27.8 (#294), Qwen3-30B-A3B: 55.9 (#138)
| Benchmark | Qwen-14B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1051 | 1384 |
| LMArena Creative Writing | 1028 | 1318 |
| LMArena Multi-Turn | 1022 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
Frequently asked questions
Is Qwen-14B better than Qwen3-30B-A3B?
Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 30.8 on the Noometry Index.
Is Qwen-14B or Qwen3-30B-A3B better for coding?
Qwen3-30B-A3B scores higher on coding benchmarks: 37.0 versus 30.6 in the Noometry coding category.
How many benchmarks do Qwen-14B and Qwen3-30B-A3B share?
11 benchmarks have published results for both models. Qwen-14B has 18 scored results on Noometry and Qwen3-30B-A3B has 32.