Qwen3 235B A22B Thinking 2507
by AlibabaRank #195Score 65.3
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
65.3
Rank
#195
24h Change
+1
7d Change
-10
State
stableConfidence
highSignal Scores
| Signal | Normalized | Weight | Contribution | Freshness |
|---|---|---|---|---|
Capabilities capability | 66.7 | 20% | 13.3 | 2026-09-22T14:25:28.831Z |
Benchmarks benchmark | 64.3 | 30% | 19.3 | 2026-09-22T14:25:28.831Z |
Pricing pricing_tier | 97.7 | 15% | 14.7 | 2026-09-22T14:25:28.831Z |
Context Window context_window | 81.2 | 10% | 8.1 | 2026-09-22T14:25:28.831Z |
Recency recency | 55.6 | 15% | 8.3 | 2026-09-22T14:25:28.831Z |
Output Capacity output_capacity | 81.1 | 10% | 8.1 | 2026-09-22T14:25:28.831Z |
Top Drivers
positive
Benchmarks
positive
Pricing
$2.30/M output tokens
$2.30
positive
Capabilities
Supports reasoning, tools, JSON mode, streaming
4/7
neutral
Recency
Released over 1 year ago
1.2y ago
Capabilities
| Capability | Supported |
|---|---|
| Vision | No |
| Reasoning | Yes |
| JSON Mode | Yes |
| Streaming | Yes |
| Function Calling | Yes |
| Web Search | No |
Pricing
Input / 1M tokens
$0.23
Output / 1M tokens
$2.30
Context Window
131K
Max Output
118K