96.4
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- adv-3002
- Model
- anthropic/claude-sonnet-4.6
- Questions asked
- 110
- Seed
- 3002
- Fingerprint
- 852970f092935a01eeb2c254
- When
- 2026-09-10T06:52:18.765987+00:00
- Duration
- 24.0 min
- Cost
- 3.96 USD billed
- Tokens
- 89.3k prompt · 614.1k completion · 703.5k total
openai/gpt-5.4
mean on this sampled test
· 0.255 USD billed
· 14.8k / 14.5k / 29.3k tok
· 2.1 s / question
92.1
openai/o4-mini
mean on this sampled test
· 0.318 USD billed
· 14.8k / 68.6k / 83.4k tok
· 5.6 s / question
95.0
qwen/qwen3-max
mean on this sampled test
· 0.148 USD billed
· 15.4k / 34.8k / 50.2k tok
· 5.0 s / question
89.3
google/gemini-2.5-pro
mean on this sampled test
· 2.42 USD billed
· 14.3k / 241.6k / 255.9k tok
· 20.5 s / question
72.9
deepseek/deepseek-r1-0528
mean on this sampled test
· 0.533 USD billed
· 14.3k / 238.4k / 252.7k tok
· 62.1 s / question
75.0
anthropic/claude-sonnet-4.6
mean on this sampled test
· 0.291 USD billed
· 15.9k / 16.2k / 32.1k tok
· 3.0 s / question
96.4