Model comparison
Qwen3 235B-A22B vs Qwen3.5-Flash
Qwen3 235B-A22B and Qwen3.5-Flash score almost the same on the Noometry Index (43.5 vs 42.5), so choose on price, context window or the category you care about most.
Last verified . 29 shared benchmarks.
Alibaba (Qwen)Summary
- They share 29 benchmarks with published results for both. Qwen3 235B-A22B scores higher in 7 categories and Qwen3.5-Flash in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5-Flash leads 33.7 to 15.7.
- The biggest single-benchmark swing is SimpleQA Verified: 40.4% for Qwen3 235B-A22B and 20.3% for Qwen3.5-Flash.
- Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.70 / $2.80 for Qwen3 235B-A22B.
- Qwen3.5-Flash accepts more context: 1M tokens versus 131K.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.
Side by side
| Qwen3 235B-A22B | Qwen3.5-Flash | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 43.5 | 42.5 |
| Released | 2025-04 | 2026-02-23 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 16K | 66K |
| Input $ / M tokens | $0.70 | $0.10 |
| Output $ / M tokens | $2.80 | $0.40 |
| 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), Qwen3.5-Flash: 34.2 (#242)
| Benchmark | Qwen3 235B-A22B | Qwen3.5-Flash |
|---|---|---|
| LMArena Coding | 1445 | 1412 |
| Aider Polyglot | 59.6% | — |
| LMArena WebDev | — | 1244 |
| SciCode | 42.4% | — |
| WeirdML | 41% | — |
| ALE-Bench | — | 221.8 |
Agentic & Tool Use Not comparable
Qwen3 235B-A22B: 33.9 (#51), Qwen3.5-Flash: —
| Benchmark | Qwen3 235B-A22B | Qwen3.5-Flash |
|---|---|---|
| Vending-Bench 2 | -11.34 | 462.69 |
| Berkeley Function Calling Leaderboard | 52.1% | — |
Reasoning Qwen3.5-Flash leads
Qwen3 235B-A22B: 15.7 (#311), Qwen3.5-Flash: 33.7 (#72)
| Benchmark | Qwen3 235B-A22B | Qwen3.5-Flash |
|---|---|---|
| Chess Puzzles | 12% | 21% |
| LMArena Hard Prompts | 1433 | 1403 |
| Mystery Game Puzzles | 9% | 20% |
| DTBench | 80.3% | 82.9% |
| LMCA | 29.3% | 29.1% |
| Epoch Capabilities Index | 143.85 | 143.98 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 11% | — |
| CritPt | 0% | — |
| ForecastBench | 59.7 | — |
Math Qwen3 235B-A22B leads
Qwen3 235B-A22B: 50.4 (#57), Qwen3.5-Flash: 37.4 (#158)
| Benchmark | Qwen3 235B-A22B | Qwen3.5-Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.7% | 84.4% |
| LMArena Math | 1432 | 1407 |
| FrontierMath (Feb 2025 set) | 8.5% | 6.2% |
| FrontierMath Tier 4 (v1) | 0% | 0% |
| FrontierMath (Tiers 1-3) | — | 18.2% |
| Omni-MATH | 71.8% | — |
| MATH Level 5 | 68.9% | — |
Knowledge Qwen3 235B-A22B leads
Qwen3 235B-A22B: 49.6 (#73), Qwen3.5-Flash: 43.2 (#93)
| Benchmark | Qwen3 235B-A22B | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 80.1% | 82.3% |
| SimpleQA Verified | 40.4% | 20.3% |
| Vectara Hallucination Rate | 9.3% | 10.5% |
| LMArena Expert | 1463 | 1407 |
| MMLU-Pro | 84.4% | — |
| Confabulations | 15.6% | — |
| GPQA (HELM) | 72.7% | — |
Multilingual Qwen3 235B-A22B leads
Qwen3 235B-A22B: 52.3 (#89), Qwen3.5-Flash: 50.5 (#121)
| Benchmark | Qwen3 235B-A22B | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1409 | 1385 |
| LMArena Chinese | 1481 | 1446 |
| LMArena French | 1445 | 1412 |
| LMArena German | 1433 | 1390 |
| LMArena Japanese | 1399 | 1368 |
| LMArena Korean | 1391 | 1344 |
| LMArena Russian | 1411 | 1379 |
| LMArena Spanish | 1430 | 1400 |
Instruction Following Too close to call
Qwen3 235B-A22B: 72.6 (#136), Qwen3.5-Flash: 72.6 (#139)
| Benchmark | Qwen3 235B-A22B | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1408 | 1374 |
| IFEval | 83.5% | — |
Long Context Qwen3 235B-A22B leads
Qwen3 235B-A22B: 46.1 (#26), Qwen3.5-Flash: 42.4 (#124)
| Benchmark | Qwen3 235B-A22B | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1426 | 1392 |
| Fiction.LiveBench | 75% | — |
Writing & Preference Qwen3 235B-A22B leads
Qwen3 235B-A22B: 59.6 (#108), Qwen3.5-Flash: 57.9 (#122)
| Benchmark | Qwen3 235B-A22B | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1419 | 1397 |
| LMArena Creative Writing | 1384 | 1343 |
| LMArena Multi-Turn | 1432 | 1393 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1366 | — |
| WildBench | 86.6% | — |
Frequently asked questions
Is Qwen3 235B-A22B better than Qwen3.5-Flash?
Qwen3 235B-A22B and Qwen3.5-Flash score almost the same on the Noometry Index (43.5 vs 42.5), so choose on price, context window or the category you care about most.
Which is cheaper, Qwen3 235B-A22B or Qwen3.5-Flash?
Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Qwen3 235B-A22B lists at $0.70 and $2.80.
Is Qwen3 235B-A22B or Qwen3.5-Flash better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5-Flash does, with 1M tokens against 131K.
How many benchmarks do Qwen3 235B-A22B and Qwen3.5-Flash share?
29 benchmarks have published results for both models. Qwen3 235B-A22B has 49 scored results on Noometry and Qwen3.5-Flash has 32.