# Qwen3 235B A22B Thinking 2507

As of October 22, 2026, Qwen3 235B A22B Thinking 2507 ranks #65 of 123 models overall with 52.9 ±25.9 on the LLMBenchmark Index. Qwen3 235B A22B Thinking 2507 ranks #32 of 108 in math, its strongest category. Qwen3 235B A22B Thinking 2507 costs $0.45 per million input tokens and $3.50 per million output tokens. Qwen3 235B A22B Thinking 2507 was released on July 25, 2025.

Page: https://llmbenchmark.ai/models/qwen3-235b-a22b-thinking-2507
Data from October 22, 2026. Every figure below names the board it was read from and the day.

- Maker: Qwen
- Released: July 25, 2025
- Price per million input tokens: $0.45
- Price per million output tokens: $3.50
- Context window: 128K tokens
- Overall rank: 65 of 123, by the LLMBenchmark Index
- LLMBenchmark Index: 52.9 ±25.9 (90% margin, from 3 of 7 inputs)
- Artificial Analysis Intelligence Index: 12.7

Benchmark results (46 of 195):

- AA Intelligence Index: 12.7 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- AA Coding Index: 22.1 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- AA Agentic Index: 1.3 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- Design Arena: websites: 1052 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: UI components: 942 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: game dev: 956 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: data viz: 950 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: 3D: 997 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: all code categories: 1032 Elo (source: Design Arena, read October 22, 2026)
- WeirdML: 41.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- GPQA Diamond (Epoch AI run): 80.1% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Mystery game puzzles: 9.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- OTIS Mock AIME: 86.7% (source: Epoch AI benchmarking hub, read October 22, 2026)
- SimpleQA Verified: 40.4% (source: Epoch AI benchmarking hub, read October 22, 2026)
- DTBench: 80.3% (source: Epoch AI benchmarking hub, read October 22, 2026)
- LMCA: 29.3% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Fiction.LiveBench: 75.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Creative writing (Lech Mazur): 82.4% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Vending-Bench 2: -$11 (source: Epoch AI benchmarking hub, read October 22, 2026)
- LMArena Text: 1415 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: coding: 1424 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts: 1416 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: math: 1412 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: instruction following: 1386 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: creative writing: 1384 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: English: 1429 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: non-English: 1397 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Chinese: 1481 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: German: 1408 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Japanese: 1386 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Korean: 1375 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Spanish: 1389 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Russian: 1401 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Polish: 1390 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: multi-turn: 1406 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: longer queries: 1400 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: expert: 1463 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts in English: 1432 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: software and IT: 1431 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: mathematical work: 1435 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: science: 1433 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: medicine and healthcare: 1456 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: legal and government: 1415 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: business and finance: 1413 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: writing and language: 1388 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: entertainment and media: 1370 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)