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
- wave7-5519
- Model
- anthropic/claude-fable-5
- Questions asked
- 177
- Seed
- 5519
- Fingerprint
- 437a8a31e9e2927239226f49
- When
- 2026-09-19T08:07:35.248953+00:00
- Duration
- 11.6 s
- Cost
- 9.74 USD billed
- Tokens
- 210.7k prompt · 728.2k completion · 938.8k total
z-ai/glm-5.3
mean on this sampled test
· 0.548 USD billed
· 25.2k / 129.5k / 154.7k tok
· 4.5 s / question
80.7
x-ai/grok-4.6
mean on this sampled test
· 1.39 USD billed
· 59.8k / 217.2k / 277.0k tok
· 11.3 s / question
97.4
moonshotai/kimi-k3
mean on this sampled test
· 1.40 USD billed
· 41.7k / 92.2k / 134.0k tok
· 8.4 s / question
93.4
openai/gpt-5.6-sol
mean on this sampled test
· 0.368 USD billed
· 24.4k / 31.9k / 56.3k tok
· 3.3 s / question
97.6
anthropic/claude-fable-5
mean on this sampled test
· 3.70 USD billed
· 36.0k / 66.8k / 102.8k tok
· 5.6 s / question
98.6
google/gemini-3.1-pro-preview
mean on this sampled test
· 2.33 USD billed
· 23.6k / 190.4k / 214.0k tok
· 8.1 s / question
57.9