Qwen3 235B A22B Thinking 2507
by AlibabaRank #149Score 64.7
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
Performance Overview
Score
64.7
Rank
#149
24h Change
+3
7d Change
-11
State
stableConfidence
highSignal Scores
| Signal | Normalized | Weight | Contribution | Freshness |
|---|---|---|---|---|
Capabilities capability | 50.0 | 20% | 10.0 | 2026-11-06T14:59:45.757Z |
Benchmarks benchmark | 64.3 | 30% | 19.3 | 2026-11-06T14:59:45.757Z |
Pricing pricing_tier | 96.5 | 15% | 14.5 | 2026-11-06T14:59:45.757Z |
Context Window context_window | 81.1 | 10% | 8.1 | 2026-11-06T14:59:45.757Z |
Recency recency | 47.4 | 15% | 7.1 | 2026-11-06T14:59:45.757Z |
Output Capacity output_capacity | 67.4 | 10% | 6.7 | 2026-11-06T14:59:45.757Z |
Top Drivers
positive
Benchmarks
positive
Pricing
$3.50/M output tokens
$3.50
neutral
Capabilities
Supports reasoning, tools, streaming
3/7
positive
Context Window
128K token context window
128K
Capabilities
| Capability | Supported |
|---|---|
| Vision | No |
| Reasoning | Yes |
| JSON Mode | No |
| Streaming | Yes |
| Function Calling | Yes |
| Web Search | No |
Pricing
Input / 1M tokens
$0.45
Output / 1M tokens
$3.50
Context Window
128K
Max Output
16K