Gemma 4 31B
Open weights
- Intelligence
- 13.9
- Rank 327 of 744 measured models
- Coding
- 33.2
- Rank 176 of 298 measured models
- Output speed
- 48 t/s
- Rank 325 of 403 measured models
- Price/1M
- $0.224
- Rank 178 of 659 measured models
- Context window
- 256K
- Rank 518 of 1199 measured models
Gemma 4 31B (Non-reasoning) scores 13.9 on the Artificial Analysis Intelligence Index, ranking 327th of 744 measured models. The closest models on this index are Grok Code Fast 1 (14.1), DeepSeek V3.1 Terminus (13.9), and Apriel-v1.5-15B-Thinker (13.8). At $0.224 per million tokens (3:1 input/output blended price), it is cheaper than DeepSeek V3.1 Terminus ($0.453). With an output speed of 48 t/s, it is faster than DeepSeek V3.1 Terminus (40.8 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Grok Code Fast 1
SpaceXSI · — · —
14.1+0.2——Compare - DeepSeek V3.1 Terminus
DeepSeek · $0.453 · 40.8 t/s
13.9$0.45340.8 t/sCompare - Apriel-v1.5-15B-Thinker
ServiceNow · — · —
13.8−0.1——Compare - DeepSeek V3.1
DeepSeek · $0.84 · 98 t/s
13.7−0.2$0.8498 t/sCompare
