- Intelligence
- 10.8
- Rank 409 of 744 measured models
- Coding
- 31.1
- Rank 181 of 298 measured models
- Output speed
- 460 t/s
- Rank 4 of 403 measured models
- Price/1M
- $0.375
- Rank 227 of 659 measured models
- Context window
- 128K
- Rank 773 of 1199 measured models
- Cost per task
- $0.0386
- Rank 31 of 193 measured models
Mercury 2 scores 10.8 on the Artificial Analysis Intelligence Index, ranking 409th of 744 measured models. The closest models on this index are Ring-1T (10.9), G9v3-3B (10.8), and Trinity Large Thinking (10.8). At $0.375 per million tokens (3:1 input/output blended price), it is priced close to Trinity Large Thinking ($0.388). With an output speed of 460 t/s, it is faster than Trinity Large Thinking (346 t/s).
Additional benchmarks8
Design Arena · 3d21.9%
Design Arena · Asciiart25.2%
Design Arena · Codecategories21.4%
Design Arena · Dataviz22.5%
Design Arena · Gamedev19.3%
Design Arena · Svg24.6%
Design Arena · Uicomponent19.6%
Design Arena · Website22.0%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Mi:dm K 2.5 Pro
Korea Telecom · — · —
11.0+0.2——Compare - Ring-1T
InclusionAI · — · —
10.9+0.1——Compare - G9v3-3B
AI9Stars · — · —
10.8——Compare - Trinity Large Thinking
Arcee AI · $0.388 · 346 t/s
10.8$0.388346 t/sCompare
