92.1
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- adv-3006
- Model
- anthropic/claude-sonnet-4.6
- Questions asked
- 110
- Seed
- 3006
- Fingerprint
- 9cccbac0afcef6847a30c0f8
- When
- 2026-09-10T07:45:08.653735+00:00
- Duration
- 7.8 min
- Cost
- 3.84 USD billed
- Tokens
- 84.0k prompt · 580.1k completion · 664.1k total
openai/gpt-5.4
mean on this sampled test
· 0.254 USD billed
· 13.9k / 14.6k / 28.5k tok
· 2.1 s / question
87.1
openai/o4-mini
mean on this sampled test
· 0.290 USD billed
· 13.9k / 62.5k / 76.4k tok
· 5.0 s / question
88.6
qwen/qwen3-max
mean on this sampled test
· 0.137 USD billed
· 14.5k / 32.3k / 46.8k tok
· 5.3 s / question
83.6
google/gemini-2.5-pro
mean on this sampled test
· 2.35 USD billed
· 13.4k / 233.9k / 247.4k tok
· 20.9 s / question
67.1
deepseek/deepseek-r1-0528
mean on this sampled test
· 0.489 USD billed
· 13.4k / 219.0k / 232.4k tok
· 62.1 s / question
70.0
anthropic/claude-sonnet-4.6
mean on this sampled test
· 0.312 USD billed
· 14.9k / 17.8k / 32.7k tok
· 3.4 s / question
92.1