92.9
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- adv-3008
- Model
- openai/o4-mini
- Questions asked
- 110
- Seed
- 3008
- Fingerprint
- 9859452d6c0189e9be51b0ed
- When
- 2026-09-10T07:58:33.933031+00:00
- Duration
- 7.8 min
- Cost
- 3.64 USD billed
- Tokens
- 86.7k prompt · 547.5k completion · 634.3k total
openai/gpt-5.4
mean on this sampled test
· 0.225 USD billed
· 14.3k / 12.6k / 27.0k tok
· 2.1 s / question
90.0
openai/o4-mini
mean on this sampled test
· 0.279 USD billed
· 14.3k / 59.9k / 74.3k tok
· 5.1 s / question
92.9
qwen/qwen3-max
mean on this sampled test
· 0.123 USD billed
· 14.9k / 28.5k / 43.4k tok
· 4.9 s / question
85.7
google/gemini-2.5-pro
mean on this sampled test
· 2.30 USD billed
· 13.9k / 229.3k / 243.2k tok
· 21.1 s / question
70.0
deepseek/deepseek-r1-0528
mean on this sampled test
· 0.458 USD billed
· 13.8k / 203.6k / 217.3k tok
· 62.1 s / question
73.6
anthropic/claude-sonnet-4.6
mean on this sampled test
· 0.251 USD billed
· 15.4k / 13.7k / 29.1k tok
· 3.1 s / question
92.9