readable AI benchmarks (simplified)
Cohere
Command A+
Command A+ has a Quality Score of 34.1, ranking 236th among 571 scored models. Per 1M tokens, pricing is $0.0000 input and $0.0000 output. It accepts text and image input, outputs text, and has a 192k token context window. Its Reliability Score is 48.0, ranking 148th among 573 scored models, above average (total average: 36.5).
Quality Score34.1coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability48.0
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- text, image
- Output modalities
- text
- Context window
- 192k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.0000
- Output
- $0.0000
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- $0.0000
Capability
- Intelligence
- 13.1
- Coding
- not available
- Agentic
- not available
- Omniscience
- -4.0
- Correct
- 8.9%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 21.8%
Correct 8.9%Incorrect 12.9%Partial / not attempted 78.2%
Artificial Analysis benchmarks
- GDPval-AA v2
- 1%
- τ³-Banking
- 6%
- SciCode
- 39%
- Humanity’s Last Exam
- 12%
- GPQA Diamond
- 76%
- CritPt
- 0%
- AA-Omniscience
- 48%
- AA-LCR
- 53%
Similar models
- North Mini CodeCohereQuality Score 20.5Value Score not available
- Command ACohereQuality Score 18.3Value Score not available
- Tiny Aya GlobalCohereQuality Score 7.6Value Score not available
- Command-R+ (Apr '24)CohereQuality Score not availableValue Score not available
- Command-R (Mar '24)CohereQuality Score not availableValue Score not available
- Grok 3 mini Reasoning (High)SpaceXAIQuality Score 34.5Value Score 29.7