Model comparison
Qwen3-30B-A3B vs Wizardlm 70b
Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 32.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)
MicrosoftSummary
- They share 12 benchmarks with published results for both. Qwen3-30B-A3B scores higher in 6 categories and Wizardlm 70b in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3-30B-A3B leads 55.9 to 34.9.
Side by side
| Qwen3-30B-A3B | Wizardlm 70b | |
|---|---|---|
| Provider | Alibaba (Qwen) | Microsoft |
| Noometry Index | 38.5 | 32.4 |
| Released | 2025-04-28 | — |
| Weights | Open | Open |
| Context window | 41K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.12 | — |
| Output $ / M tokens | $0.50 | — |
| Results tracked | 32 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-30B-A3B leads
Qwen3-30B-A3B: 37.0 (#188), Wizardlm 70b: 30.9 (#280)
| Benchmark | Qwen3-30B-A3B | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1416 | 1081 |
| SciCode | 33.3% | — |
| WeirdML | 29.8% | — |
Agentic & Tool Use Not comparable
Qwen3-30B-A3B: 29.5 (#75), Wizardlm 70b: —
| Benchmark | Qwen3-30B-A3B | Wizardlm 70b |
|---|---|---|
| Berkeley Function Calling Leaderboard | 41.4% | — |
Reasoning Qwen3-30B-A3B leads
Qwen3-30B-A3B: 21.6 (#193), Wizardlm 70b: 19.8 (#231)
| Benchmark | Qwen3-30B-A3B | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1398 | 1079 |
| Kagi LLM Benchmark | 54.9% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | 8% | — |
| DTBench | 69.3% | — |
| LMCA | 22.4% | — |
| Epoch Capabilities Index | 139.63 | — |
Math Qwen3-30B-A3B leads
Qwen3-30B-A3B: 36.0 (#133), Wizardlm 70b: 29.7 (#216)
| Benchmark | Qwen3-30B-A3B | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1394 | 1116 |
| MathArena Final-Answer Competitions | 47.8% | — |
| OTIS Mock AIME 2024-2025 | 70.3% | — |
Knowledge Not comparable
Qwen3-30B-A3B: 41.7 (#96), Wizardlm 70b: —
| Benchmark | Qwen3-30B-A3B | Wizardlm 70b |
|---|---|---|
| GPQA Diamond | 70.1% | — |
| Confabulations | 12.3% | — |
| LMArena Expert | 1395 | — |
Multilingual Qwen3-30B-A3B leads
Qwen3-30B-A3B: 49.8 (#126), Wizardlm 70b: 29.8 (#260)
| Benchmark | Qwen3-30B-A3B | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1372 | 1078 |
| LMArena Chinese | 1434 | 1052 |
| LMArena German | 1379 | 1083 |
| LMArena Russian | 1369 | 1155 |
| LMArena French | 1419 | — |
| LMArena Japanese | 1338 | — |
| LMArena Korean | 1333 | — |
| LMArena Spanish | 1403 | — |
Instruction Following Qwen3-30B-A3B leads
Qwen3-30B-A3B: 72.2 (#137), Wizardlm 70b: 56.5 (#268)
| Benchmark | Qwen3-30B-A3B | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1364 | 1093 |
Long Context Wizardlm 70b leads
Qwen3-30B-A3B: 31.0 (#278), Wizardlm 70b: 33.3 (#258)
| Benchmark | Qwen3-30B-A3B | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1379 | 1097 |
| Fiction.LiveBench | 40.6% | — |
Writing & Preference Qwen3-30B-A3B leads
Qwen3-30B-A3B: 55.9 (#138), Wizardlm 70b: 34.9 (#264)
| Benchmark | Qwen3-30B-A3B | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1384 | 1120 |
| LMArena Creative Writing | 1318 | 1149 |
| LMArena Multi-Turn | 1378 | 1108 |
| Short-Story Creative Writing | 75.3% | — |
Frequently asked questions
Is Qwen3-30B-A3B better than Wizardlm 70b?
Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 32.4 on the Noometry Index.
Is Qwen3-30B-A3B or Wizardlm 70b better for coding?
Qwen3-30B-A3B scores higher on coding benchmarks: 37.0 versus 30.9 in the Noometry coding category.
How many benchmarks do Qwen3-30B-A3B and Wizardlm 70b share?
12 benchmarks have published results for both models. Qwen3-30B-A3B has 32 scored results on Noometry and Wizardlm 70b has 12.