# Qwen3.5-35B-A3B

As of October 21, 2026, Qwen3.5-35B-A3B ranks #62 of 123 models overall with 53.5 ±13.6 on the LLMBenchmark Index. Qwen3.5-35B-A3B ranks #59 of 108 in math, its strongest category. Qwen3.5-35B-A3B costs $0.1625 per million input tokens and $1.30 per million output tokens. Qwen3.5-35B-A3B was released on February 25, 2026.

Page: https://llmbenchmark.ai/models/qwen3-5-35b-a3b
Data from October 21, 2026. Every figure below names the board it was read from and the day.

- Maker: Qwen
- Released: February 25, 2026
- Price per million input tokens: $0.1625
- Price per million output tokens: $1.30
- Context window: 262K tokens
- Overall rank: 62 of 123, by the LLMBenchmark Index
- LLMBenchmark Index: 53.5 ±13.6 (90% margin, from 4 of 7 inputs)
- Artificial Analysis Intelligence Index: 19.3
- Vibe Coding Index: not enough data (one index benchmark; at least two are needed to rank)

Benchmark results (45 of 195):

- LMArena WebDev: 1254 Elo (source: LMArena WebDev, read October 21, 2026)
- AA Intelligence Index: 19.3 (source: Artificial Analysis (via OpenRouter), read October 21, 2026)
- GPQA Diamond (Artificial Analysis run): 84.5% (source: Artificial Analysis, read October 21, 2026)
- Humanity's Last Exam (Artificial Analysis run): 21.0% (source: Artificial Analysis, read October 21, 2026)
- Terminal-Bench Hard (Artificial Analysis run): 26.5% (source: Artificial Analysis, read October 21, 2026)
- IFBench: 72.5% (source: Artificial Analysis, read October 21, 2026)
- Long context reasoning (AA-LCR): 72.0% (source: Artificial Analysis, read October 21, 2026)
- τ²-Bench Telecom: 89.2% (source: Artificial Analysis, read October 21, 2026)
- GPQA Diamond (Epoch AI run): 83.5% (source: Epoch AI benchmarking hub, read October 21, 2026)
- OTIS Mock AIME: 70.0% (source: Epoch AI benchmarking hub, read October 21, 2026)
- DTBench: 80.0% (source: Epoch AI benchmarking hub, read October 21, 2026)
- LMCA: 29.5% (source: Epoch AI benchmarking hub, read October 21, 2026)
- ALE-Bench: 221.8 (source: ALE-Bench (Sakana AI), read October 21, 2026)
- Vending-Bench 2: $463 (source: Epoch AI benchmarking hub, read October 21, 2026)
- Epoch Capabilities Index: 142.5 (source: Epoch AI benchmarking hub, read October 21, 2026)
- LMArena Text: 1395 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: coding: 1410 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: hard prompts: 1400 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: math: 1404 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: instruction following: 1379 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: creative writing: 1347 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: English: 1407 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: non-English: 1378 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Chinese: 1457 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: German: 1367 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Japanese: 1326 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Korean: 1355 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: French: 1412 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Spanish: 1390 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Russian: 1376 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Polish: 1385 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: multi-turn: 1390 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: longer queries: 1389 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: expert: 1408 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: hard prompts in English: 1411 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: software and IT: 1415 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: mathematical work: 1410 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: science: 1413 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: medicine and healthcare: 1421 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: legal and government: 1399 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: business and finance: 1394 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: writing and language: 1365 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: entertainment and media: 1347 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena WebDev: React: 1238 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena WebDev: HTML: 1301 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)