Model comparison
ScoreVision-v2 vs Claude 4 Sonnet
Capability radar, value bars, and side-by-side posture.
ScoreVision-v2
Not scored
value score
Claude 4 Sonnet
91
value score
ScoreVision-v2 ctx
—
Claude 4 Sonnet ctx
200K
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- Claude 4 Sonnet91
Attribute tape
| Field | ScoreVision-v2 | Claude 4 Sonnet |
|---|---|---|
| Developer | Unknown | Anthropic |
| Context | — | 200K |
| Modalities | Text, Code, Image | |
| Openness | — | Proprietary Model |
| Speed | — | Fast |
| Price | — | $3/1M in · $15/1M out |
| Value score | — | 91 |
| Summary | ScoreVision-v2 is a computer-vision model published on Hugging Face by user stfkramer, focused on game-state recognition (GSR) for football video — extracting structured data such as player/ball positions and pitch keypoints from match footage. It appears associated with Score / Subnet 44 on the Bittensor decentralized AI network. | Balanced Claude model for coding and agents. |