Qwen2.5 VL 72B Instruct
by AlibabaRank #391Score 40.0
Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.
Performance Overview
Score
40.0
Rank
#391
24h Change
0
7d Change
0
State
stableConfidence
highSignal Scores
| Signal | Normalized | Weight | Contribution | Freshness |
|---|---|---|---|---|
Capabilities capability | 50.0 | 30% | 15.0 | 2026-09-22T14:25:04.207Z |
Pricing pricing_tier | 99.0 | 25% | 24.8 | 2026-09-22T14:25:04.207Z |
Context Window context_window | 81.1 | 15% | 12.2 | 2026-09-22T14:25:04.207Z |
Recency recency | 24.0 | 15% | 3.6 | 2026-09-22T14:25:04.207Z |
Output Capacity output_capacity | 80.9 | 15% | 12.1 | 2026-09-22T14:25:04.207Z |
Top Drivers
positive
Pricing
$1.00/M output tokens
$1.00
neutral
Capabilities
Supports vision, JSON mode, streaming
3/7
positive
Context Window
128K token context window
128K
positive
Output Capacity
Up to 115K output tokens per request
115K
Capabilities
| Capability | Supported |
|---|---|
| Vision | Yes |
| Reasoning | No |
| JSON Mode | Yes |
| Streaming | Yes |
| Function Calling | No |
| Web Search | No |
Pricing
Input / 1M tokens
$0.80
Output / 1M tokens
$1.00
Context Window
128K
Max Output
115K