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-3005
- Model
- anthropic/claude-sonnet-4.6
- Questions asked
- 110
- Seed
- 3005
- Fingerprint
- 521ff180e3e3c325c89f70ea
- When
- 2026-09-10T07:37:22.913877+00:00
- Duration
- 10.4 min
- Cost
- 3.85 USD billed
- Tokens
- 88.0k prompt · 577.2k completion · 665.3k total
openai/gpt-5.4
mean on this sampled test
· 0.240 USD billed
· 14.6k / 13.6k / 28.2k tok
· 1.9 s / question
92.1
openai/o4-mini
mean on this sampled test
· 0.277 USD billed
· 14.4k / 59.4k / 73.8k tok
· 4.5 s / question
92.9
qwen/qwen3-max
mean on this sampled test
· 0.136 USD billed
· 15.2k / 31.7k / 46.9k tok
· 5.2 s / question
88.6
google/gemini-2.5-pro
mean on this sampled test
· 2.46 USD billed
· 14.1k / 244.1k / 258.3k tok
· 20.7 s / question
71.4
deepseek/deepseek-r1-0528
mean on this sampled test
· 0.480 USD billed
· 13.9k / 214.2k / 228.1k tok
· 61.4 s / question
72.1
anthropic/claude-sonnet-4.6
mean on this sampled test
· 0.260 USD billed
· 15.7k / 14.2k / 29.9k tok
· 3.0 s / question
95.0