readable AI benchmarks (simplified)
Meta
Muse Spark 1.1 (xhigh)
Muse Spark 1.1 (xhigh) has a Quality Score of 61.2, ranking 19th among 53 scored models. Per 1M tokens, pricing is $1.25 input, $4.25 output, and $0.150 cached input. Its Reliability Score is 59.0, ranking 16th among 53 scored models, above average (total average: 50.1). Its Value Score is 44.5, around average compared with the total Value average of 39.6.
Quality Score61.2coverage 91.2%: missing Epoch General ECI, CursorBench 3.2 and DeepSWE v1.1
Value Score44.5
Reliability59.0
Cache Discount88%
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- not available
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $1.25
- Output
- $4.25
- Cached Input
- $0.150
- Cache write
- not available
- Cost per task
- $0.261
Capability
- Intelligence
- 50.6
- Coding
- 71.3
- Agentic
- 37.5
- Omniscience
- 18.0
- Correct
- 40.6%
- Blended price
- $0.780
Answer outcomes
Attempt rate: 63.2%
Correct 40.6%Incorrect 22.6%Abstained 36.8%
Artificial Analysis benchmarks
- GDPval-AA v2
- 44%
- τ³-Banking
- 25%
- Terminal-Bench v2.1
- 78%
- SciCode
- 58%
- Humanity’s Last Exam
- 45%
- GPQA Diamond
- 90%
- CritPt
- 15%
- AA-Omniscience
- 59%
- AA-LCR
- 63%
Similar models
- Muse SparkMetaQuality Score 54.3Value Score not available
- Claude Sonnet 5 (max)AnthropicQuality Score 61.4Value Score 42.1
- GPT-5.5 (medium)OpenAIQuality Score 63.4Value Score 38.7
- Claude Opus 5 (low)AnthropicQuality Score 64.1Value Score 38.8
- GPT-5.6 Sol (low)OpenAIQuality Score 63.6Value Score 38.4
- GPT-5.6 Terra (xhigh)OpenAIQuality Score 58.3Value Score 40.9