97.8
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- wave7-5509
- Model
- anthropic/claude-fable-5
- Questions asked
- 177
- Seed
- 5509
- Fingerprint
- bd497a851a86c03224919d55
- When
- 2026-09-19T08:01:16.107611+00:00
- Duration
- 1.7 min
- Cost
- 10.35 USD billed
- Tokens
- 209.7k prompt · 780.1k completion · 989.9k total
z-ai/glm-5.3
mean on this sampled test
· 0.577 USD billed
· 24.9k / 136.9k / 161.8k tok
· 5.3 s / question
78.6
x-ai/grok-4.6
mean on this sampled test
· 1.55 USD billed
· 59.7k / 242.6k / 302.3k tok
· 11.6 s / question
96.8
moonshotai/kimi-k3
mean on this sampled test
· 1.55 USD billed
· 41.7k / 102.1k / 143.8k tok
· 9.0 s / question
90.6
openai/gpt-5.6-sol
mean on this sampled test
· 0.361 USD billed
· 24.3k / 31.3k / 55.6k tok
· 3.4 s / question
95.6
anthropic/claude-fable-5
mean on this sampled test
· 3.92 USD billed
· 35.7k / 71.2k / 106.9k tok
· 5.7 s / question
97.8
google/gemini-3.1-pro-preview
mean on this sampled test
· 2.40 USD billed
· 23.5k / 196.0k / 219.5k tok
· 9.0 s / question
58.0