Qwen3 30B A3B Thinking 2507
by AlibabaRank #199Score 64.1
Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...
Performance Overview
Score
64.1
Rank
#199
24h Change
+1
7d Change
-9
State
stableConfidence
highSignal Scores
| Signal | Normalized | Weight | Contribution | Freshness |
|---|---|---|---|---|
Capabilities capability | 66.7 | 20% | 13.3 | 2026-09-22T14:25:28.382Z |
Benchmarks benchmark | 64.7 | 30% | 19.4 | 2026-09-22T14:25:28.382Z |
Pricing pricing_tier | 97.6 | 15% | 14.6 | 2026-09-22T14:25:28.382Z |
Context Window context_window | 78.0 | 10% | 7.8 | 2026-09-22T14:25:28.382Z |
Recency recency | 61.8 | 15% | 9.3 | 2026-09-22T14:25:28.382Z |
Output Capacity output_capacity | 72.2 | 10% | 7.2 | 2026-09-22T14:25:28.382Z |
Top Drivers
positive
Benchmarks
positive
Pricing
$2.40/M output tokens
$2.40
positive
Capabilities
Supports reasoning, tools, JSON mode, streaming
4/7
positive
Recency
Released over 1 year ago
1.1y ago
Capabilities
| Capability | Supported |
|---|---|
| Vision | No |
| Reasoning | Yes |
| JSON Mode | Yes |
| Streaming | Yes |
| Function Calling | Yes |
| Web Search | No |
Pricing
Input / 1M tokens
$0.20
Output / 1M tokens
$2.40
Context Window
82K
Max Output
33K