98.6
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- wave7-5503
- Model
- openai/gpt-5.6-sol
- Questions asked
- 177
- Seed
- 5503
- Fingerprint
- 9a228fa14a7d90e60ce97d34
- When
- 2026-09-19T07:49:55.599834+00:00
- Duration
- 3.6 min
- Cost
- 10.29 USD billed
- Tokens
- 210.6k prompt · 761.5k completion · 972.1k total
z-ai/glm-5.3
mean on this sampled test
· 0.594 USD billed
· 25.2k / 139.0k / 164.2k tok
· 4.9 s / question
80.9
x-ai/grok-4.6
mean on this sampled test
· 1.41 USD billed
· 59.8k / 219.7k / 279.5k tok
· 10.4 s / question
98.2
moonshotai/kimi-k3
mean on this sampled test
· 1.65 USD billed
· 42.0k / 108.7k / 150.7k tok
· 8.1 s / question
94.4
openai/gpt-5.6-sol
mean on this sampled test
· 0.377 USD billed
· 24.5k / 32.8k / 57.3k tok
· 3.6 s / question
98.6
anthropic/claude-fable-5
mean on this sampled test
· 3.94 USD billed
· 35.5k / 71.7k / 107.2k tok
· 5.8 s / question
98.2
google/gemini-3.1-pro-preview
mean on this sampled test
· 2.32 USD billed
· 23.6k / 189.5k / 213.2k tok
· 8.6 s / question
59.2