Model comparison
Qwen3 235B-A22B vs Qwen3-30B-A3B
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 5.7× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.
Last verified . 31 shared benchmarks.
Alibaba (Qwen)Summary
- They share 31 benchmarks with published results for both. Qwen3 235B-A22B scores higher in 8 categories and Qwen3-30B-A3B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Qwen3 235B-A22B leads 46.1 to 31.0.
- The biggest single-benchmark swing is Fiction.LiveBench: 75% for Qwen3 235B-A22B and 40.6% for Qwen3-30B-A3B.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.70 / $2.80 for Qwen3 235B-A22B.
- Qwen3 235B-A22B accepts more context: 131K tokens versus 41K.
Side by side
| Qwen3 235B-A22B | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 43.5 | 38.9 |
| Released | 2025-04 | 2025-04-28 |
| Weights | Open | Open |
| Context window | 131K | 41K |
| Max output | 16K | 16K |
| Input $ / M tokens | $0.70 | $0.12 |
| Output $ / M tokens | $2.80 | $0.50 |
| Results tracked | 49 | 32 |
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), Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | Qwen3 235B-A22B | Qwen3-30B-A3B |
|---|---|---|
| SciCode | 42.4% | 33.3% |
| WeirdML | 41% | 29.8% |
| LMArena Coding | 1445 | 1416 |
| Aider Polyglot | 59.6% | — |
Agentic & Tool Use Qwen3 235B-A22B leads
Qwen3 235B-A22B: 33.9 (#51), Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | Qwen3 235B-A22B | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 52.1% | 41.4% |
| Vending-Bench 2 | -11.34 | — |
Reasoning Qwen3-30B-A3B leads
Qwen3 235B-A22B: 15.7 (#311), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | Qwen3 235B-A22B | Qwen3-30B-A3B |
|---|---|---|
| Kagi LLM Benchmark | 69.4% | 54.9% |
| CritPt | 0% | 0.3% |
| Chess Puzzles | 12% | 8% |
| LMArena Hard Prompts | 1433 | 1398 |
| DTBench | 80.3% | 69.3% |
| LMCA | 29.3% | 22.4% |
| Epoch Capabilities Index | 143.85 | 139.63 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31% | — |
| ARC-AGI-1 | 11% | — |
| Mystery Game Puzzles | 9% | — |
| ForecastBench | 59.7 | — |
Math Qwen3 235B-A22B leads
Qwen3 235B-A22B: 50.4 (#57), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | Qwen3 235B-A22B | Qwen3-30B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.7% | 70.3% |
| LMArena Math | 1432 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| Omni-MATH | 71.8% | — |
| MATH Level 5 | 68.9% | — |
| FrontierMath (Feb 2025 set) | 8.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Qwen3 235B-A22B leads
Qwen3 235B-A22B: 49.6 (#73), Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | Qwen3 235B-A22B | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | 80.1% | 70.1% |
| Confabulations | 15.6% | 12.3% |
| LMArena Expert | 1463 | 1396 |
| SimpleQA Verified | 40.4% | — |
| MMLU-Pro | 84.4% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 72.7% | — |
Multilingual Qwen3 235B-A22B leads
Qwen3 235B-A22B: 52.3 (#89), Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | Qwen3 235B-A22B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1409 | 1372 |
| LMArena Chinese | 1481 | 1433 |
| LMArena French | 1445 | 1418 |
| LMArena German | 1433 | 1380 |
| LMArena Japanese | 1399 | 1337 |
| LMArena Korean | 1391 | 1331 |
| LMArena Russian | 1411 | 1370 |
| LMArena Spanish | 1430 | 1404 |
Instruction Following Too close to call
Qwen3 235B-A22B: 72.6 (#136), Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | Qwen3 235B-A22B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1408 | 1363 |
| IFEval | 83.5% | — |
Long Context Qwen3 235B-A22B leads
Qwen3 235B-A22B: 46.1 (#26), Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | Qwen3 235B-A22B | Qwen3-30B-A3B |
|---|---|---|
| Fiction.LiveBench | 75% | 40.6% |
| LMArena Longer Query | 1426 | 1379 |
Writing & Preference Qwen3 235B-A22B leads
Qwen3 235B-A22B: 59.6 (#108), Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | Qwen3 235B-A22B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1419 | 1384 |
| LMArena Creative Writing | 1384 | 1317 |
| Short-Story Creative Writing | 83% | 75.3% |
| LMArena Multi-Turn | 1432 | 1378 |
| EQ-Bench Creative Writing | 1366 | — |
| WildBench | 86.6% | — |
Frequently asked questions
Is Qwen3 235B-A22B better than Qwen3-30B-A3B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 5.7× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.
Which is cheaper, Qwen3 235B-A22B or Qwen3-30B-A3B?
Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; Qwen3 235B-A22B lists at $0.70 and $2.80.
Is Qwen3 235B-A22B or Qwen3-30B-A3B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 37.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3 235B-A22B does, with 131K tokens against 41K.
How many benchmarks do Qwen3 235B-A22B and Qwen3-30B-A3B share?
31 benchmarks have published results for both models. Qwen3 235B-A22B has 49 scored results on Noometry and Qwen3-30B-A3B has 32.