GMP Bench
← Back to Leaderboard

Llama 4 Scout

OpenRouterCloud-scale
Overall Score
56.2%

65 evaluations

GMP Knowledge
93.2%

44 evals

Task Completion
47.0%

18 evals

Multimodal
26.4%

3 evals, scored separately

Avg Latency
16.2s

across all evals

Score by Category