ModelCap

Current AI model comparison

Exact identities · public evidence

Qwen

Qwen3 235B A22B Instruct 2507

Position

#85

Index

59.8

Measured

2 public benchmark observations across 2 boards

Comparison side 1

Qwen

Qwen3 235B A22B Thinking 2507

Position

#114

Index

52.8

Measured

2 public benchmark observations across 2 boards

Comparison side 2

Output / 1M

$0.80

vs $3.50

Context

262K

vs 128K

Weights

Open weights

vs Open weights