Qwen3 Coder 480B A35B
ModelOpen sourceActiveby Alibaba (Qwen) · family “qwen3-coderb-a35b”
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over... (description from the OpenRouter listing)
in: textout: textTool useStructured output
Epoch Capabilities Index
Not scored by Epoch AI
Released
23 Jul 2025
Context window
262K tokens
Max output
66K tokens
Input $ / 1M tokens
$0.30
Output $ / 1M tokens
$1.00
Cached input $ / 1M
$0.10
Each benchmark shown separately with its own source
Benchmark results (3)
| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| GSO-Bench | coding | 4.9% | 10% | — | — | External ↗ |
| Terminal Bench | agents | 27.2% ±2.6 | 32% | agent: Dakou Agent | 22 Jul 2025 | External ↗ |
| WeirdML | coding | 41.2% ±0.0 | 44% | — | — | External ↗ |
Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.
API list price over time
Price history
$ per 1M tokens
13 observations (OpenRouter listing + Internet Archive snapshots). History accumulates with every ingest run; a single point means no change has been observed yet.
Events
No events recorded yet.