95.0
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- adv-3009
- Model
- anthropic/claude-sonnet-4.6
- Questions asked
- 110
- Seed
- 3009
- Fingerprint
- a338ca323284c5153481d9f9
- When
- 2026-09-10T08:03:23.533463+00:00
- Duration
- 4.7 min
- Cost
- 3.94 USD billed
- Tokens
- 87.4k prompt · 598.4k completion · 685.8k total
openai/gpt-5.4
mean on this sampled test
· 0.259 USD billed
· 14.5k / 14.9k / 29.3k tok
· 2.1 s / question
90.7
openai/o4-mini
mean on this sampled test
· 0.305 USD billed
· 14.5k / 65.8k / 80.3k tok
· 5.4 s / question
92.9
qwen/qwen3-max
mean on this sampled test
· 0.146 USD billed
· 15.1k / 34.4k / 49.5k tok
· 5.2 s / question
87.1
google/gemini-2.5-pro
mean on this sampled test
· 2.43 USD billed
· 14.0k / 242.1k / 256.1k tok
· 21.9 s / question
70.0
deepseek/deepseek-r1-0528
mean on this sampled test
· 0.502 USD billed
· 13.8k / 224.6k / 238.3k tok
· 62.1 s / question
72.1
anthropic/claude-sonnet-4.6
mean on this sampled test
· 0.296 USD billed
· 15.6k / 16.6k / 32.2k tok
· 3.2 s / question
95.0