readable AI benchmarks (simplified)
Reflection
Beam 1.0
Beam 1.0 has a Quality Score of 48.7, ranking 101st among 398 scored models. Per 1M tokens, pricing is $0.700 input, $2.10 output, and $0.115 cached input. It has a 1,048,576 token context window. Its Reliability Score is 50.8, ranking 97th among 399 scored models, above average (total average: 38.0). Its Value Score is 37.7, around average compared with the total Value average of 33.2.
Quality Score48.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score37.7
Factual reliability50.8
Cache Discount84%
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 1,048,576 tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.700
- Output
- $2.10
- Cached Input
- $0.115
- Cache write
- not available
- Cost per task
- $0.566
Capability
- Intelligence
- 30.3
- Coding
- not available
- Agentic
- not available
- Omniscience
- 1.5
- Correct
- 33.1%
- Blended price
- $0.431
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 64.6%
Correct 33.1%Incorrect 31.6%Partial / not attempted 35.4%
Similar models
- Kimi K3 (Low)KimiQuality Score 49.1Value Score 31.1
- Claude Haiku 5.5 (Low)AnthropicQuality Score 48.5Value Score 44.3
- Claude Sonnet 5 (High)AnthropicQuality Score 48.4Value Score 32.2
- K2 Horizon 375B A23BInstitute of Foundation ModelsQuality Score 47.7Value Score not available
- MiniMax-M3MiniMaxQuality Score 47.8Value Score 39.9
- GPT-6 Luna (High)OpenAIQuality Score 49.0Value Score 44.8