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
- wave7-5504
- Model
- anthropic/claude-fable-5
- Questions asked
- 177
- Seed
- 5504
- Fingerprint
- e0c6a88d04b20b76bc77ba8d
- When
- 2026-09-19T07:51:47.944431+00:00
- Duration
- 1.9 min
- Cost
- 10.19 USD billed
- Tokens
- 210.3k prompt · 776.7k completion · 987.0k total
z-ai/glm-5.3
mean on this sampled test
· 0.547 USD billed
· 25.1k / 130.1k / 155.2k tok
· 4.8 s / question
80.8
x-ai/grok-4.6
mean on this sampled test
· 1.58 USD billed
· 59.8k / 247.5k / 307.3k tok
· 11.9 s / question
96.0
moonshotai/kimi-k3
mean on this sampled test
· 1.49 USD billed
· 41.7k / 99.3k / 141.0k tok
· 8.1 s / question
92.8
openai/gpt-5.6-sol
mean on this sampled test
· 0.383 USD billed
· 24.4k / 33.4k / 57.8k tok
· 3.5 s / question
95.6
anthropic/claude-fable-5
mean on this sampled test
· 3.77 USD billed
· 35.8k / 68.2k / 104.0k tok
· 5.8 s / question
98.4
google/gemini-3.1-pro-preview
mean on this sampled test
· 2.43 USD billed
· 23.5k / 198.2k / 221.7k tok
· 9.6 s / question
56.8