- Intelligence
- 25.0
- Rank 174 of 744 measured models
- Coding
- 52.1
- Rank 115 of 298 measured models
- Output speed
- 180 t/s
- Rank 48 of 403 measured models
- Price/1M
- $1.76
- Rank 455 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
Inkling (Xhigh) scores 25.0 on the Artificial Analysis Intelligence Index, ranking 174th of 744 measured models. The closest models on this index are MiMo-V2-Omni-0327 (25.1), GPT-5 Codex (High) (24.9), and Grok 4.3 (24.9). At $1.76 per million tokens (3:1 input/output blended price), it is cheaper than GPT-5 Codex (High) ($3.44), more expensive than Grok 4.3 ($1.56). With an output speed of 180 t/s, it is faster than GPT-5 Codex (High) (166 t/s) and Grok 4.3 (94.6 t/s).
Additional benchmarks9
Design Arena · 3d40.1%
Design Arena · Asciiart33.9%
Design Arena · Codecategories42.2%
Design Arena · Dataviz37.9%
Design Arena · Gamedev37.9%
Design Arena · Svg35.0%
Design Arena · Uicomponent40.2%
Design Arena · Webapps48.6%
Design Arena · Website44.6%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Grok 4.20 0309
SpaceXSI · $3 · —
25.2+0.2$3—Compare - MiMo-V2-Omni-0327
Xiaomi · — · —
25.1+0.1——Compare - GPT-5 Codex (High)
OpenAI · $3.44 · 166 t/s
24.9−0.1$3.44166 t/sCompare - Grok 4.3
SpaceXSI · $1.56 · 94.6 t/s
24.9−0.1$1.5694.6 t/sCompare
