ModelCap

Current AI model comparison

Exact identities · public evidence

Qwen

Qwen3 235B A22B Instruct 2507

Position

#56

Index

57.6

Measured

2 public benchmark observations across 2 boards

Comparison side 1

Stepfun Ai

Step3 VL 10B

Position

#53

Index

59.1

Estimated

global-corpus-prior over 186 held-out anchors (18%); launch card against 2 resolved peers on 4 rows (82%); exceeds every named peer on 3 of 4 rows; no cross-lab optimism probe available; shrunk 1.5 toward the measured corpus

Comparison side 2

Output / 1M

$0.35

vs Unavailable

Context

262K

vs

Weights

Open weights

vs Open weights