- Intelligence
- 14.2
- Rank 321 of 744 measured models
- Coding
- 31.0
- Rank 182 of 298 measured models
- Output speed
- 112 t/s
- Rank 152 of 403 measured models
- Price/1M
- $0.15
- Rank 128 of 659 measured models
- Context window
- 262K
- Rank 458 of 1199 measured models
Gemma 4 12B (Reasoning) scores 14.2 on the Artificial Analysis Intelligence Index, ranking 321st of 744 measured models. The closest models on this index are ERNIE 5.0 Thinking Preview (14.3), Mistral Medium 3.5 (14.2), and Grok Code Fast 1 (14.1). At $0.15 per million tokens (3:1 input/output blended price), it is cheaper than Mistral Medium 3.5 ($3). With an output speed of 112 t/s, it is slower than Mistral Medium 3.5 (151 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- K-EXAONE
LG AI Research · — · —
14.4+0.2——Compare - ERNIE 5.0 Thinking Preview
Baidu · — · —
14.3+0.1——Compare - Mistral Medium 3.5
Mistral · $3 · 151 t/s
14.2$3151 t/sCompare - Grok Code Fast 1
SpaceXSI · — · —
14.1−0.1——Compare
