- Intelligence
- 22.7
- Rank 209 of 744 measured models
- Coding
- 58.8
- Rank 89 of 298 measured models
- Price/1M
- $0.10
- Rank 90 of 659 measured models
- Context window
- 256K
- Rank 518 of 1199 measured models
Hy3-preview (Reasoning) scores 22.7 on the Artificial Analysis Intelligence Index, ranking 209th of 744 measured models. The closest models on this index are MiniMax-M2.5 (22.8), GPT-5.5 Instant (May 2026) (22.7), and Ling-3.0-flash-Fin (22.6). At $0.10 per million tokens (3:1 input/output blended price), it is cheaper than MiniMax-M2.5 ($0.525), GPT-5.5 Instant (May 2026) ($11.25), and Ling-3.0-flash-Fin ($0.111).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Nemotron 3 Ultra 550B A55B
NVIDIA · $1.08 · 155 t/s
22.9+0.2$1.08155 t/sCompare - MiniMax-M2.5
MiniMax · $0.525 · 66.5 t/s
22.8+0.1$0.52566.5 t/sCompare - GPT-5.5 Instant (May 2026)
OpenAI · $11.25 · —
22.7$11.25—Compare - Ling-3.0-flash-Fin
InclusionAI · $0.111 · 272 t/s
22.6−0.1$0.111272 t/sCompare
