98.4
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- wave7-5520
- Model
- openai/gpt-5.6-sol
- Questions asked
- 177
- Seed
- 5520
- Fingerprint
- 4db6fd669b410cb578c420be
- When
- 2026-09-19T08:07:51.508315+00:00
- Duration
- 15.9 s
- Cost
- 10.10 USD billed
- Tokens
- 208.5k prompt · 758.0k completion · 966.5k total
z-ai/glm-5.3
mean on this sampled test
· 0.554 USD billed
· 24.9k / 131.4k / 156.2k tok
· 4.5 s / question
81.1
x-ai/grok-4.6
mean on this sampled test
· 1.47 USD billed
· 59.5k / 230.2k / 289.8k tok
· 10.8 s / question
98.2
moonshotai/kimi-k3
mean on this sampled test
· 1.55 USD billed
· 41.7k / 103.8k / 145.6k tok
· 8.1 s / question
93.6
openai/gpt-5.6-sol
mean on this sampled test
· 0.388 USD billed
· 24.1k / 34.0k / 58.2k tok
· 3.5 s / question
98.4
anthropic/claude-fable-5
mean on this sampled test
· 3.83 USD billed
· 35.0k / 69.5k / 104.5k tok
· 5.7 s / question
98.0
google/gemini-3.1-pro-preview
mean on this sampled test
· 2.31 USD billed
· 23.3k / 189.0k / 212.3k tok
· 8.2 s / question
59.8