81.4
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- adv-3001
- Model
- anthropic/claude-sonnet-4.6
- Questions asked
- 110
- Seed
- 3001
- Fingerprint
- 596d3412e678b8f84841be58
- When
- 2026-09-10T06:11:28.399952+00:00
- Duration
- 67.2 min
- Cost
- 3.22 USD billed
- Tokens
- 70.5k prompt · 467.7k completion · 538.2k total
openai/gpt-5.4
mean on this sampled test
· 0.210 USD billed
· 11.8k / 12.0k / 23.9k tok
· 2.4 s / question
79.3
openai/o4-mini
mean on this sampled test
· 0.244 USD billed
· 11.7k / 52.6k / 64.3k tok
· 6.4 s / question
80.7
qwen/qwen3-max
mean on this sampled test
· 0.112 USD billed
· 12.3k / 26.1k / 38.5k tok
· 5.8 s / question
75.7
google/gemini-2.5-pro
mean on this sampled test
· 2.06 USD billed
· 11.4k / 204.5k / 215.9k tok
· 30.4 s / question
59.3
deepseek/deepseek-r1-0528
mean on this sampled test
· 0.357 USD billed
· 10.4k / 159.3k / 169.7k tok
· 62.1 s / question
57.9
anthropic/claude-sonnet-4.6
mean on this sampled test
· 0.235 USD billed
· 12.7k / 13.2k / 25.9k tok
· 3.5 s / question
81.4