Qwen3 30B A3B Instruct 2507
by AlibabaRank #200Score 64.1
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...
Performance Overview
Score
64.1
Rank
#200
24h Change
+1
7d Change
+170
State
stableConfidence
highSignal Scores
| Signal | Normalized | Weight | Contribution | Freshness |
|---|---|---|---|---|
Capabilities capability | 50.0 | 30% | 15.0 | 2026-09-22T14:25:05.483Z |
Pricing pricing_tier | 99.8 | 25% | 25.0 | 2026-09-22T14:25:05.483Z |
Context Window context_window | 86.0 | 15% | 12.9 | 2026-09-22T14:25:05.483Z |
Recency recency | 56.4 | 15% | 8.5 | 2026-09-22T14:25:05.483Z |
Output Capacity output_capacity | 72.0 | 15% | 10.8 | 2026-09-22T14:25:05.483Z |
Top Drivers
positive
Pricing
$0.19/M output tokens
$0.19
neutral
Capabilities
Supports tools, JSON mode, streaming
3/7
positive
Context Window
262K token context window
262K
positive
Output Capacity
Up to 32K output tokens per request
32K
Capabilities
| Capability | Supported |
|---|---|
| Vision | No |
| Reasoning | No |
| JSON Mode | Yes |
| Streaming | Yes |
| Function Calling | Yes |
| Web Search | No |
Pricing
Input / 1M tokens
$0.05
Output / 1M tokens
$0.19
Context Window
262K
Max Output
32K