FIBRE
Leaderboard
Compare
Methodology
Compare
Pick up to three models. Everything below updates against the same 202 tasks.
opus-5
kimi-k3
qwen3.8-max
gpt-5.6-sol
glm-5.3
haiku-5.5-high
opus-4.6
deepseek-v4p1-flash
sonnet-5
gpt-5.5
gpt-5.6-terra
minimax-m3
gpt-5.6-luna
haiku-4.5