DASHBOARD

results over the last 7 days — who's slacking?

SPEED LEADERBOARD

mistral/mistral-small-latest 441ms
CHEAP
mistral/mistral-medium-latest 552ms
MID
google/gemini-3.1-flash-lite-preview 569ms
anthropic/claude-haiku-4-5 572ms
CHEAP
openai/gpt-5.4 589ms
MID
openai/gpt-5.4-mini 593ms
CHEAP
google/gemini-3.1-flash-lite 594ms
CHEAP
google/gemini-3-flash-preview 1156ms
MID
deepseek/deepseek-v4-flash 1342ms
MID
anthropic/claude-opus-4-7 1529ms
FLAGSHIP
anthropic/claude-sonnet-4-6 1587ms
MID
deepseek/deepseek-v4-pro 1628ms
FLAGSHIP
mistral/mistral-large-latest 1808ms
FLAGSHIP
openai/gpt-5.5 1992ms
FLAGSHIP
google/gemini-3.1-pro-preview 3527ms
FLAGSHIP

7-DAY UPTIME

anthropic/claude-haiku-4-5 100%
CHEAP 5039/5040 probes
anthropic/claude-sonnet-4-6 100%
MID 5035/5040 probes
deepseek/deepseek-v4-flash 100%
MID 5034/5040 probes
deepseek/deepseek-v4-pro 100%
FLAGSHIP 5032/5040 probes
google/gemini-3.1-flash-lite 100%
CHEAP 5040/5040 probes
google/gemini-3.1-pro-preview 100%
FLAGSHIP 1680/1680 probes
google/gemini-3-flash-preview 100%
MID 5036/5040 probes
mistral/mistral-large-latest 100%
FLAGSHIP 5039/5040 probes
mistral/mistral-medium-latest 100%
MID 5040/5040 probes
mistral/mistral-small-latest 100%
CHEAP 5032/5040 probes
anthropic/claude-opus-4-7 99%
FLAGSHIP 4972/5040 probes
google/gemini-3.1-flash-lite-preview -
openai/gpt-5.4 -
MID
openai/gpt-5.4-mini -
CHEAP
openai/gpt-5.5 -
FLAGSHIP

WRONG ANSWERS

% of successful probes where the model did NOT return the expected response · lower is better · daily over 7 days

daily averages in your local timezone · only successful probes