Alibaba (Qwen), open weights

# Qwen3 235B-A22B

> Qwen3 235B-A22B by Alibaba (Qwen), released April 2025. Ranked #91 of 354 with a Noometry Index of 43.5. API: $0.70 in / $2.80 out per M tokens. 131K context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/qwen3-235b-a22b
- Last updated: 2026-10-10
- Title: Qwen3 235B-A22B Benchmarks, Price & Rank (October 2026)

Qwen3 235B-A22B by Alibaba (Qwen) ranks 91st of 354 ranked models on the Noometry Index as of October 2026, with a score of 43.5. Its strongest category is long context, where it ranks 26th. API pricing starts at $0.70 per million input tokens and $2.80 per million output tokens, with a 131K-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #91 of 354
- **Index score:** 43.5
- **Evidence:** Confirmed 49 results
- **Provider:** [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba)
- **Released:** April 1, 2025
- **Weights:** Open weights
- **Reasoning:** Yes
- **Context window:** 131K
- **Max output:** 16K
- **Input price:** $0.70 / M
- **Output price:** $2.80 / M
- **Blended price:** $1.22 / M
- **Output speed:** 85 tokens/s [Kagi](https://help.kagi.com/kagi/ai/llm-benchmark.html)
- **Value:** #126 of 219
- **Knowledge cutoff:** April 2025
- **Input:** text
- **Hugging Face:** [Qwen/Qwen3-235B-A22B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507)

## Category scores

Each category score combines every public result we have in that category.

Qwen3 235B-A22B category scores

1.  Coding 44.3
2.  Agentic & Tool Use 33.9
3.  Reasoning 15.7
4.  Math 50.4
5.  Knowledge 49.6
6.  Multilingual 52.3
7.  Instruction Following 72.6
8.  Long Context 46.1
9.  Writing & Preference 59.6
10.  020406080

Qwen3 235B-A22B category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 44.3 | #75 | 4 |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 33.9 | #51 | 1 |
| [Reasoning](https://noometry.com/best/reasoning) | 15.7 | #311 | 10 |
| [Math](https://noometry.com/best/math) | 50.4 | #57 | 4 |
| [Knowledge](https://noometry.com/best/knowledge) | 49.6 | #73 | 7 |
| [Multilingual](https://noometry.com/best/multilingual) | 52.3 | #89 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 72.6 | #136 | 2 |
| [Long Context](https://noometry.com/best/long-context) | 46.1 | #26 | 2 |
| [Writing & Preference](https://noometry.com/best/writing) | 59.6 | #108 | 6 |

## Strengths and weaknesses

Categories where Qwen3 235B-A22B places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

Qwen3 235B-A22B: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Long Context](https://noometry.com/best/long-context) | 46.1 | +5.2 | #26 of 296, top 9% |
| [Math](https://noometry.com/best/math) | 50.4 | +13.8 | #57 of 327, top 18% |
| [Coding](https://noometry.com/best/coding) | 44.3 | +5.5 | #75 of 340, top 23% |

### Weakest categories

Qwen3 235B-A22B: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Reasoning](https://noometry.com/best/reasoning) | 15.7 | −7.9 | #311 of 350, top 89% |
| [Instruction Following](https://noometry.com/best/instruction-following) | 72.6 | +1.3 | #136 of 305, top 45% |
| [Writing & Preference](https://noometry.com/best/writing) | 59.6 | +5.8 | #108 of 312, top 35% |

## Closest competitors

The models ranked just above and below Qwen3 235B-A22B. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Qwen3 235B-A22B
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [Qwen3 Max](https://noometry.com/models/qwen3-max) | #87 | 43.7 | $2.40 | 48 | [Compare](https://noometry.com/compare/qwen3-235b-a22b-vs-qwen3-max) |
| [MiMo-V2-Omni](https://noometry.com/models/mimo-v2-omni) | #88 | 43.6 | $0.18 | — | [Compare](https://noometry.com/compare/mimo-v2-omni-vs-qwen3-235b-a22b) |
| [Kimi K2.5 Instant](https://noometry.com/models/kimi-k2-5-instant) | #89 | 43.6 | — | — | [Compare](https://noometry.com/compare/kimi-k2-5-instant-vs-qwen3-235b-a22b) |
| [Gemma 4 31B IT](https://noometry.com/models/gemma-4-31b-it) | #90 | 43.5 | $0.15 | 3 | [Compare](https://noometry.com/compare/gemma-4-31b-it-vs-qwen3-235b-a22b) |
| [Gemma 4 26B A4B IT](https://noometry.com/models/gemma-4-26b-a4b-it) | #92 | 43.5 | $0.11 | — | [Compare](https://noometry.com/compare/gemma-4-26b-a4b-it-vs-qwen3-235b-a22b) |
| [MiMo-V2.5](https://noometry.com/models/mimo-v2-5) | #93 | 43.4 | $0.18 | — | [Compare](https://noometry.com/compare/mimo-v2-5-vs-qwen3-235b-a22b) |
| [Kimi K2.7 Code](https://noometry.com/models/kimi-k2-7-code) | #94 | 43.3 | $1.71 | — | [Compare](https://noometry.com/compare/kimi-k2-7-code-vs-qwen3-235b-a22b) |
| [Qwen3-VL 235B-A22B](https://noometry.com/models/qwen3-vl-235b-a22b) | #95 | 43.2 | $1.22 | — | [Compare](https://noometry.com/compare/qwen3-235b-a22b-vs-qwen3-vl-235b-a22b) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

### Coding

Qwen3 235B-A22B Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Aider Polyglot](https://noometry.com/benchmarks/aider-polyglot) | 59.6% | #14 of 44, top 32% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Aider Polyglot](https://noometry.com/benchmarks/aider-polyglot) | 59.6% | #14 of 44, top 32% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SciCode](https://noometry.com/benchmarks/scicode) | 42.4% | #70 of 121, top 58% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 38.7% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 41% | #74 of 119, top 63% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 38.7% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 37.3% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1445 | #94 of 294, top 32% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1424 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1398 |  | no-thinking | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Agentic & Tool Use

Qwen3 235B-A22B Agentic & Tool Use benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Berkeley Function Calling Leaderboard](https://noometry.com/benchmarks/bfcl) | 52.1% | #17 of 49, top 35% | prompt | [Berkeley Function Calling Leaderboard](https://gorilla.cs.berkeley.edu/leaderboard.html) |  |
| [Vending-Bench 2](https://noometry.com/benchmarks/vending-bench-2) | \-11.34 | #57 of 60, top 95% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Reasoning

Qwen3 235B-A22B Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 1.3% | #68 of 83, top 82% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SimpleBench](https://noometry.com/benchmarks/simplebench) | 31% | #60 of 77, top 78% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) | 55% |  |  | [Kagi LLM Benchmark](https://help.kagi.com/kagi/ai/llm-benchmark.html) |  |
| [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) | 69.4% | #26 of 99, top 27% |  | [Kagi LLM Benchmark](https://help.kagi.com/kagi/ai/llm-benchmark.html) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 11% | #73 of 83, top 88% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CritPt](https://noometry.com/benchmarks/critpt) | 0% | #131 of 134, top 98% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 12% | #80 of 129, top 63% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1433 | #88 of 297, top 30% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1416 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1393 |  | no-thinking | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 9% | #63 of 74, top 86% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 78.4% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 75.7% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 80.3% | #74 of 151, top 50% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 25% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 29.3% | #76 of 125, top 61% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 23.5% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 143.85 | #90 of 213, top 43% |  | [Epoch AI](https://epoch.ai/eci) | 2025-07-25 |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 138.92 |  |  | [Epoch AI](https://epoch.ai/eci) | 2025-07-25 |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 139.35 |  |  | [Epoch AI](https://epoch.ai/eci) | 2025-04-28 |
| [ForecastBench](https://noometry.com/benchmarks/forecastbench) | 59.7 | #36 of 72, top 50% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Math

Qwen3 235B-A22B Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 86.7% | #63 of 173, top 37% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-10 |
| [Omni-MATH](https://noometry.com/benchmarks/omni-math) | 71.8% | #3 of 57, top 6% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [Omni-MATH](https://noometry.com/benchmarks/omni-math) | 54.8% |  |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1432 | #81 of 285, top 29% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1412 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1397 |  | no-thinking | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [MATH Level 5](https://noometry.com/benchmarks/math-level-5) | 68.9% | #32 of 79, top 41% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-06-03 |
| [FrontierMath (Feb 2025 set)](https://noometry.com/benchmarks/frontiermath-2025-02) | 8.5% | #39 of 68, top 58% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [FrontierMath Tier 4 (v1)](https://noometry.com/benchmarks/frontiermath-tier-4-v1) | 0% | #53 of 55, top 97% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |

### Knowledge

Qwen3 235B-A22B Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 80.1% | #79 of 186, top 43% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-11 |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 70.7% |  |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-06-03 |
| [SimpleQA Verified](https://noometry.com/benchmarks/simpleqa-verified) | 40.4% | #43 of 77, top 56% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [MMLU-Pro](https://noometry.com/benchmarks/mmlu-pro) | 81.7% |  |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [MMLU-Pro](https://noometry.com/benchmarks/mmlu-pro) | 84.4% | #8 of 58, top 14% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [Confabulations](https://noometry.com/benchmarks/confabulations) (lower is better) | 16.8% |  |  | [Lech Mazur benchmarks](https://github.com/lechmazur/confabulations) |  |
| [Confabulations](https://noometry.com/benchmarks/confabulations) (lower is better) | 15.6% | #20 of 51, top 40% |  | [Lech Mazur benchmarks](https://github.com/lechmazur/confabulations) |  |
| [Vectara Hallucination Rate](https://noometry.com/benchmarks/vectara-hallucination) (lower is better) | 9.3% | #47 of 96, top 49% |  | [Vectara Hallucination Leaderboard](https://github.com/vectara/hallucination-leaderboard) |  |
| [GPQA (HELM)](https://noometry.com/benchmarks/helm-gpqa) | 72.7% | #8 of 57, top 15% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [GPQA (HELM)](https://noometry.com/benchmarks/helm-gpqa) | 62.3% |  |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1442 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1463 | #58 of 273, top 22% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1369 |  | no-thinking | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Multilingual

Qwen3 235B-A22B Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1409 | #88 of 297, top 30% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1397 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1384 |  | no-thinking | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1465 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1481 | #62 of 285, top 22% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1425 |  | no-thinking | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1445 | #80 of 223, top 36% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1369 |  | no-thinking | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1387 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1408 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1433 | #62 of 231, top 27% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1386 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1399 | #60 of 211, top 29% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1371 |  | no-thinking | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1391 | #68 of 213, top 32% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1375 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1358 |  | no-thinking | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1400 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1411 | #94 of 283, top 34% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1394 |  | no-thinking | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1389 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1430 | #83 of 226, top 37% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1403 |  | no-thinking | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

Qwen3 235B-A22B Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [IFEval](https://noometry.com/benchmarks/ifeval) | 81.6% |  |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [IFEval](https://noometry.com/benchmarks/ifeval) | 83.5% | #28 of 57, top 50% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1386 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1408 | #90 of 298, top 31% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1362 |  | no-thinking | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

Qwen3 235B-A22B Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Fiction.LiveBench](https://noometry.com/benchmarks/fiction-livebench) | 75% | #15 of 47, top 32% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Fiction.LiveBench](https://noometry.com/benchmarks/fiction-livebench) | 67.7% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Fiction.LiveBench](https://noometry.com/benchmarks/fiction-livebench) | 52.9% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1400 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1426 | #84 of 291, top 29% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1389 |  | no-thinking | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

Qwen3 235B-A22B Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1415 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1419 | #96 of 297, top 33% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1394 |  | no-thinking | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1384 | #102 of 295, top 35% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1375 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1356 |  | no-thinking | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [Short-Story Creative Writing](https://noometry.com/benchmarks/lech-mazur-writing) | 82.4% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Short-Story Creative Writing](https://noometry.com/benchmarks/lech-mazur-writing) | 83% | #10 of 39, top 26% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [EQ-Bench Creative Writing](https://noometry.com/benchmarks/eqbench-creative-writing) | 1366 | #73 of 115, top 64% |  | [EQ-Bench](https://eqbench.com/creative_writing.html) |  |
| [WildBench](https://noometry.com/benchmarks/wildbench) | 86.6% | Best of 57 |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [WildBench](https://noometry.com/benchmarks/wildbench) | 82.8% |  |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1432 | #81 of 295, top 28% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1406 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1398 |  | no-thinking | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## API pricing by provider

Qwen3 235B-A22B API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [alibaba](https://www.alibabacloud.com/help/en/model-studio/models) | $0.70 | $2.80 | — | 2026-10-10 |
| [bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) | $0.22 | $0.88 | — | 2026-10-10 |
| [deepinfra](https://deepinfra.com/models) | $0.09 | $0.55 | — | 2026-10-10 |
| [openrouter](https://openrouter.ai/qwen/qwen3-235b-a22b-2507) | $0.09 | $0.55 | — | 2026-10-10 |
| [together](https://docs.together.ai/docs/serverless-models) | $0.20 | $0.60 | — | 2026-10-10 |
| [vertex](https://cloud.google.com/vertex-ai/generative-ai/docs/models) | $0.22 | $0.88 | — | 2026-10-10 |

[All Alibaba (Qwen) API prices →](https://noometry.com/llm-pricing/alibaba) [Estimate your cost →](https://noometry.com/tools/cost-calculator)

## Compare Qwen3 235B-A22B

-   [Qwen3 235B-A22B vs Qwen2-72B](https://noometry.com/compare/qwen2-72b-vs-qwen3-235b-a22b)
-   [Qwen3 235B-A22B vs Gemma 4 31B IT](https://noometry.com/compare/gemma-4-31b-it-vs-qwen3-235b-a22b)
-   [Qwen3 235B-A22B vs Gemma 4 26B A4B IT](https://noometry.com/compare/gemma-4-26b-a4b-it-vs-qwen3-235b-a22b)
-   [Qwen3 235B-A22B vs Kimi K2.5 Instant](https://noometry.com/compare/kimi-k2-5-instant-vs-qwen3-235b-a22b)
-   [Qwen3 235B-A22B vs MiMo-V2.5](https://noometry.com/compare/mimo-v2-5-vs-qwen3-235b-a22b)
-   [Qwen3 235B-A22B vs MiMo-V2-Omni](https://noometry.com/compare/mimo-v2-omni-vs-qwen3-235b-a22b)
-   [Qwen3 235B-A22B vs Kimi K2.7 Code](https://noometry.com/compare/kimi-k2-7-code-vs-qwen3-235b-a22b)
-   [Qwen3 235B-A22B vs GPT-6 Astra](https://noometry.com/compare/gpt-6-astra-vs-qwen3-235b-a22b)
-   [Qwen3 235B-A22B vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-qwen3-235b-a22b)
-   [Qwen3 235B-A22B vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-qwen3-235b-a22b)
-   [Qwen3 235B-A22B vs Kimi K3](https://noometry.com/compare/kimi-k3-vs-qwen3-235b-a22b)
-   [Qwen3 235B-A22B vs Grok 4.6](https://noometry.com/compare/grok-4-6-vs-qwen3-235b-a22b)
-   [Qwen3 235B-A22B vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-qwen3-235b-a22b)
-   [Qwen3 235B-A22B vs Muse Spark 1.3](https://noometry.com/compare/muse-spark-1-3-vs-qwen3-235b-a22b)

## Other Alibaba (Qwen) models

-   [Qwen3.8 Max](https://noometry.com/models/qwen3-8-max)56.8
-   [Qwen3.7 Max](https://noometry.com/models/qwen3-7-max)51.5
-   [Qwen3.6 Max Preview](https://noometry.com/models/qwen3-6-max-preview)51.5
-   [Qwen3.6 Plus](https://noometry.com/models/qwen3-6-plus)47.5
-   [Qwen3.5 397B-A17B](https://noometry.com/models/qwen3-5-397b-a17b)46.0
-   [Qwen3.8 27B](https://noometry.com/models/qwen3-8-27b)46.0
-   [Qwen3.5 Max Preview](https://noometry.com/models/qwen3-5-max-preview)45.3
-   [Qwen3.7 Plus](https://noometry.com/models/qwen3-7-plus)45.3

## Frequently asked questions

### How good is Qwen3 235B-A22B?

Qwen3 235B-A22B by Alibaba (Qwen) ranks 91st of 354 ranked models on the Noometry Index as of October 2026, with a score of 43.5. Its strongest category is long context, where it ranks 26th. API pricing starts at $0.70 per million input tokens and $2.80 per million output tokens, with a 131K-token context window.

### How much does Qwen3 235B-A22B cost?

Qwen3 235B-A22B costs $0.70 per million input tokens and $2.80 per million output tokens on Alibaba (Qwen)'s own API.

### What is Qwen3 235B-A22B's context window?

Qwen3 235B-A22B accepts up to 131K tokens of input and can write up to 16K tokens in one response.

### Is Qwen3 235B-A22B open source?

Yes. Qwen3 235B-A22B's weights are downloadable from Hugging Face (Qwen/Qwen3-235B-A22B-Instruct-2507); check the license for commercial terms.

### How fast is Qwen3 235B-A22B?

Qwen3 235B-A22B generated about 85 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.

### What are Qwen3 235B-A22B's strengths and weaknesses?

Relative to other ranked models, Qwen3 235B-A22B places best in long context, math, coding and lowest in reasoning, instruction following, writing & preference.

### What is Qwen3 235B-A22B best at?

Its best category is long context, where it ranks 26th on Noometry.

### Cite this page

Noometry. (2026). Qwen3 235B-A22B benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/qwen3-235b-a22b

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/qwen3-235b-a22b.md).