99.0
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- wave7-5510
- Model
- openai/gpt-5.6-sol
- Questions asked
- 177
- Seed
- 5510
- Fingerprint
- cec7d324ff71a1d51623dbc7
- When
- 2026-09-19T08:02:39.615519+00:00
- Duration
- 82.8 s
- Cost
- 9.92 USD billed
- Tokens
- 210.3k prompt · 746.6k completion · 956.9k total
z-ai/glm-5.3
mean on this sampled test
· 0.558 USD billed
· 25.2k / 132.0k / 157.1k tok
· 4.4 s / question
80.5
x-ai/grok-4.6
mean on this sampled test
· 1.45 USD billed
· 59.8k / 226.3k / 286.1k tok
· 11.3 s / question
98.1
moonshotai/kimi-k3
mean on this sampled test
· 1.63 USD billed
· 41.7k / 107.7k / 149.4k tok
· 8.0 s / question
93.8
openai/gpt-5.6-sol
mean on this sampled test
· 0.363 USD billed
· 24.5k / 31.4k / 55.9k tok
· 3.4 s / question
99.0
anthropic/claude-fable-5
mean on this sampled test
· 3.67 USD billed
· 35.6k / 66.3k / 101.9k tok
· 5.4 s / question
97.7
google/gemini-3.1-pro-preview
mean on this sampled test
· 2.24 USD billed
· 23.6k / 182.9k / 206.5k tok
· 7.6 s / question
61.3