Model comparison
Qwen3 235B-A22B vs Wizardlm 70b
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 33.0 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)
MicrosoftSummary
- They share 12 benchmarks with published results for both. Qwen3 235B-A22B 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 235B-A22B leads 59.6 to 34.8.
Side by side
| Qwen3 235B-A22B | Wizardlm 70b | |
|---|---|---|
| Provider | Alibaba (Qwen) | Microsoft |
| Noometry Index | 43.5 | 33.0 |
| Released | 2025-04 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.70 | — |
| Output $ / M tokens | $2.80 | — |
| Results tracked | 49 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Qwen3 235B-A22B: 44.3 (#75), Wizardlm 70b: 31.4 (#285)
| Benchmark | Qwen3 235B-A22B | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1445 | 1081 |
| Aider Polyglot | 59.6% | — |
| SciCode | 42.4% | — |
| WeirdML | 41% | — |
Agentic & Tool Use Not comparable
Qwen3 235B-A22B: 33.9 (#51), Wizardlm 70b: —
| Benchmark | Qwen3 235B-A22B | Wizardlm 70b |
|---|---|---|
| Berkeley Function Calling Leaderboard | 52.1% | — |
| Vending-Bench 2 | -11.34 | — |
Reasoning Wizardlm 70b leads
Qwen3 235B-A22B: 15.7 (#311), Wizardlm 70b: 20.7 (#234)
| Benchmark | Qwen3 235B-A22B | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1433 | 1079 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 11% | — |
| CritPt | 0% | — |
| Chess Puzzles | 12% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 80.3% | — |
| LMCA | 29.3% | — |
| Epoch Capabilities Index | 143.85 | — |
| ForecastBench | 59.7 | — |
Math Qwen3 235B-A22B leads
Qwen3 235B-A22B: 50.4 (#57), Wizardlm 70b: 32.2 (#218)
| Benchmark | Qwen3 235B-A22B | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1432 | 1116 |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| Omni-MATH | 71.8% | — |
| MATH Level 5 | 68.9% | — |
| FrontierMath (Feb 2025 set) | 8.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Not comparable
Qwen3 235B-A22B: 49.6 (#73), Wizardlm 70b: —
| Benchmark | Qwen3 235B-A22B | Wizardlm 70b |
|---|---|---|
| GPQA Diamond | 80.1% | — |
| SimpleQA Verified | 40.4% | — |
| MMLU-Pro | 84.4% | — |
| Confabulations | 15.6% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 72.7% | — |
| LMArena Expert | 1463 | — |
Multilingual Qwen3 235B-A22B leads
Qwen3 235B-A22B: 52.3 (#89), Wizardlm 70b: 29.6 (#265)
| Benchmark | Qwen3 235B-A22B | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1409 | 1078 |
| LMArena Chinese | 1481 | 1052 |
| LMArena German | 1433 | 1083 |
| LMArena Russian | 1411 | 1155 |
| LMArena French | 1445 | — |
| LMArena Japanese | 1399 | — |
| LMArena Korean | 1391 | — |
| LMArena Spanish | 1430 | — |
Instruction Following Qwen3 235B-A22B leads
Qwen3 235B-A22B: 72.6 (#136), Wizardlm 70b: 56.3 (#273)
| Benchmark | Qwen3 235B-A22B | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1408 | 1093 |
| IFEval | 83.5% | — |
Long Context Qwen3 235B-A22B leads
Qwen3 235B-A22B: 46.1 (#26), Wizardlm 70b: 33.3 (#263)
| Benchmark | Qwen3 235B-A22B | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1426 | 1097 |
| Fiction.LiveBench | 75% | — |
Writing & Preference Qwen3 235B-A22B leads
Qwen3 235B-A22B: 59.6 (#108), Wizardlm 70b: 34.8 (#269)
| Benchmark | Qwen3 235B-A22B | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1419 | 1120 |
| LMArena Creative Writing | 1384 | 1149 |
| LMArena Multi-Turn | 1432 | 1108 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1366 | — |
| WildBench | 86.6% | — |
Frequently asked questions
Is Qwen3 235B-A22B better than Wizardlm 70b?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 33.0 on the Noometry Index.
Is Qwen3 235B-A22B or Wizardlm 70b better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 31.4 in the Noometry coding category.
How many benchmarks do Qwen3 235B-A22B and Wizardlm 70b share?
12 benchmarks have published results for both models. Qwen3 235B-A22B has 49 scored results on Noometry and Wizardlm 70b has 12.