97.4
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- wave7-5506
- Model
- openai/gpt-5.6-sol
- Questions asked
- 177
- Seed
- 5506
- Fingerprint
- f67ad02724c90ee6d66c9ce0
- When
- 2026-09-19T07:54:33.960605+00:00
- Duration
- 79.3 s
- Cost
- 10.58 USD billed
- Tokens
- 212.6k prompt · 803.1k completion · 1.02M total
z-ai/glm-5.3
mean on this sampled test
· 0.570 USD billed
· 25.5k / 137.6k / 163.1k tok
· 4.9 s / question
81.2
x-ai/grok-4.6
mean on this sampled test
· 1.61 USD billed
· 60.1k / 253.6k / 313.7k tok
· 11.9 s / question
95.4
moonshotai/kimi-k3
mean on this sampled test
· 1.69 USD billed
· 42.2k / 112.8k / 155.0k tok
· 9.9 s / question
93.3
openai/gpt-5.6-sol
mean on this sampled test
· 0.386 USD billed
· 24.7k / 33.6k / 58.4k tok
· 3.4 s / question
97.4
anthropic/claude-fable-5
mean on this sampled test
· 3.95 USD billed
· 36.2k / 71.8k / 108.0k tok
· 5.7 s / question
97.2
google/gemini-3.1-pro-preview
mean on this sampled test
· 2.37 USD billed
· 23.9k / 193.7k / 217.6k tok
· 9.3 s / question
58.5