Using {{model}} performance on {{sample_benchmarks}}, predict scores on {{target_benchmarks}}. Known results: - {{benchmark_1}}: {{score_1}} - {{benchmark_2}}: {{score_2}} - {{benchmark_3}}: {{score_3}} Predict remaining benchmark scores with confidence intervals.
82 copies0 forks
Details
Category
AnalysisUse Cases
Performance predictionBenchmark estimationCapability forecasting
Works Best With
claude-opus-4.5gpt-5.2gemini-2.0-flash
Created Shared