- Intelligence
- 30.3
- Rank 125 of 748 measured models
- Output speed
- 228 t/s
- Rank 29 of 409 measured models
- Price/1M
- $1.05
- Rank 393 of 668 measured models
- Context window
- 1M
- Rank 85 of 1213 measured models
- Cost per task
- $0.566
- Rank 113 of 197 measured models
Beam 1.0 scores 30.3 on the Artificial Analysis Intelligence Index, ranking 125th of 748 measured models. The closest models on this index are K2 Horizon 375B A23B (30.5), DeepSeek V4 Pro 0424 (30.4), and GPT-5.2 (30.4). At $1.05 per million tokens (3:1 input/output blended price), it is cheaper than GPT-5.2 ($4.81), more expensive than DeepSeek V4 Pro 0424 ($0.544). With an output speed of 228 t/s, it is faster than DeepSeek V4 Pro 0424 (84 t/s) and GPT-5.2 (77.6 t/s), slower than K2 Horizon 375B A23B (1,213 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- K2 Horizon 375B A23B
Institute of Foundation Models · — · 1,213 t/s
30.5+0.2—1,213 t/sCompare - DeepSeek V4 Pro 0424
DeepSeek · $0.544 · 84 t/s
30.4+0.1$0.54484 t/sCompare - GPT-5.2
OpenAI · $4.81 · 77.6 t/s
30.4+0.1$4.8177.6 t/sCompare - Claude Sonnet 4.6 (batch)
Anthropic · — · —
30.1−0.2——Compare
