readable AI benchmarks (simplified)
Meta
Muse Spark 1.2 (Xhigh)
Muse Spark 1.2 (Xhigh) has a Quality Score of 62.2, ranking 55th among 577 scored models. Per 1M tokens, pricing is $1.25 input, $4.25 output, and $0.150 cached input. It accepts text, image, video, pdf, and audio input, outputs text, and has a 1,048,576 token context window. Its Reliability Score is 63.6, ranking 41st among 579 scored models, above average (total average: 36.6). Its Value Score is 44.9, high compared with the total Value average of 31.8.
Model specification
- Reasoning
- reasoning
- Input modalities
- text, image, video, pdf, audio
- Output modalities
- text
- Context window
- 1,048,576 tokens
- 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
- $0.975
Capability
- Intelligence
- 39.6
- Coding
- not available
- Agentic
- not available
- Omniscience
- 27.2
- Correct
- 45.4%
- Blended price
- $0.780
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 63.6%
Artificial Analysis benchmarks
- GDPval-AA v2
- 49%
- τ³-Banking
- 35%
- SciCode
- 57%
- Humanity’s Last Exam
- 45%
- GPQA Diamond
- 90%
- CritPt
- 18%
- AA-Omniscience
- 64%
- AA-LCR
- 79%
DeepSWE operational cross-check
- Pass@1
- 54.9%
- Avg steps/scored attempt
- 100.76
- Mean cost/scored attempt (USD)
- $3.70
- Mean output tokens/scored attempt
- 99,226.381
- Mean duration/scored attempt (s)
- 928 s
Mean cost/scored attempt is the official feed's mean_cost_usd: mean benchmark cost in USD per scored attempt under the source's cost basis. It is not Artificial Analysis cost per task and not token price (USD per 1M tokens). Mean output tokens/scored attempt is mean_output_tokens, also averaged over every scored attempt including scored failures. Mean duration/scored attempt is mean_duration_seconds; it is informational only, and wall-clock varies with provider and host load. These three fields do not affect Quality Score, Value Score, or Reliability. Epoch General ECI's benchmark basket includes DeepSWE v1.1, so Epoch General ECI and this DeepSWE cross-check are not independent evidence.
Similar models
- Muse Spark 1.3 (Xhigh)MetaQuality Score 65.5Value Score 47.2
- Muse Spark 1.1 (Xhigh)MetaQuality Score 58.0Value Score 41.8
- Muse Spark 1.3 (Max)MetaQuality Score 68.2Value Score 49.2
- Muse SparkMetaQuality Score 50.9Value Score not available
- Muse Glimmer (High)MetaQuality Score 30.2Value Score 25.1
- Llama 3.1 Instruct 405BMetaQuality Score 26.3Value Score not available