Model Compare

GPT-6.1 Sol · high

openai-codex/gpt-6.1-sol · thinking high · benchmark e52f92182965

TaskOutcomeTimeTokensCost
Beaconcomplete 393.1 s195,309 $0.21
Periodic Table Dashboardcomplete 526 s381,736 $0.29
The Lighthouse Keepercomplete 322.7 s137,533 $0.19
Voicemailscomplete 154.9 s14,199 $0.04
TokenBucket Docscomplete 67.7 s7,761 $0.03
Ride Analysiscomplete 903.1 s1,213,419 $0.55
huddle-api PR #1 Reviewcomplete 154.6 s63,885 $0.09

Compare with other models at compare.littleplanetlabs.dev.