# Qwen3 Coder 480B A35B

As of October 21, 2026, Qwen3 Coder 480B A35B ranks #141 of 213 models overall with 11.9 on the Artificial Analysis Intelligence Index. Its strongest category is coding, where it ranks #76 of 136. Qwen3 Coder 480B A35B costs $0.30 per million input tokens and $1.00 per million output tokens. It was released on July 23, 2025.

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

- Maker: Qwen
- Released: July 23, 2025
- Price per million input tokens: $0.30
- Price per million output tokens: $1.00
- Context window: 262K tokens
- Overall rank: 141 of 213, by the Artificial Analysis Intelligence Index
- Artificial Analysis Intelligence Index: 11.9
- Vibe Coding Index: 50.0 (from 2 of 4 coding benchmarks)

Benchmark results (52 of 190):

- SWE-bench Verified: 69.6% (source: SWE-bench (swebench.com), read October 21, 2026)
- LMArena WebDev: 1275 Elo (source: LMArena WebDev, read October 21, 2026)
- AA Intelligence Index: 11.9 (source: Artificial Analysis (via OpenRouter), read October 21, 2026)
- Design Arena: websites: 1159 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: UI components: 1112 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: game dev: 1099 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: data viz: 1084 Elo (source: Design Arena, read October 21, 2026)
- Design Arena: all code categories: 1143 Elo (source: Design Arena, read October 21, 2026)
- AA Math Index: 39.3 (source: Artificial Analysis, read October 21, 2026)
- GPQA Diamond (Artificial Analysis run): 61.8% (source: Artificial Analysis, read October 21, 2026)
- Humanity's Last Exam (Artificial Analysis run): 4.5% (source: Artificial Analysis, read October 21, 2026)
- MMLU Pro (Artificial Analysis run): 78.8% (source: Artificial Analysis, read October 21, 2026)
- LiveCodeBench (Artificial Analysis run): 58.5% (source: Artificial Analysis, read October 21, 2026)
- Terminal-Bench Hard (Artificial Analysis run): 18.9% (source: Artificial Analysis, read October 21, 2026)
- IFBench: 40.5% (source: Artificial Analysis, read October 21, 2026)
- Long context reasoning (AA-LCR): 45.7% (source: Artificial Analysis, read October 21, 2026)
- τ²-Bench Telecom: 43.6% (source: Artificial Analysis, read October 21, 2026)
- AIME 2025 (Artificial Analysis run): 39.3% (source: Artificial Analysis, read October 21, 2026)
- Terminal-Bench: 27.2% (source: Epoch AI benchmarking hub, read October 21, 2026)
- GSO-Bench: 4.9% (source: Epoch AI benchmarking hub, read October 21, 2026)
- WeirdML: 41.2% (source: Epoch AI benchmarking hub, read October 21, 2026)
- ALE-Bench: 461.4 (source: ALE-Bench (Sakana AI), read October 21, 2026)
- LMArena Text: 1357 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: coding: 1412 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: hard prompts: 1372 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: math: 1365 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: instruction following: 1355 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: creative writing: 1333 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: English: 1359 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: non-English: 1346 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Chinese: 1357 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: German: 1325 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Japanese: 1311 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Korean: 1305 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: French: 1398 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Spanish: 1360 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Russian: 1366 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Polish: 1344 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: multi-turn: 1366 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: longer queries: 1378 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: expert: 1338 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: hard prompts in English: 1380 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: software and IT: 1393 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: mathematical work: 1367 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: science: 1347 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: medicine and healthcare: 1347 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: legal and government: 1358 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: business and finance: 1343 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: writing and language: 1340 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: entertainment and media: 1317 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena WebDev: React: 1257 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena WebDev: HTML: 1287 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)