96.2
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- wave5-5303
- Model
- openai/gpt-5.6-luna-pro
- Questions asked
- 177
- Seed
- 5303
- Fingerprint
- 8566579c1ff4d5fadbc3dfc0
- When
- 2026-09-18T16:13:27.888493+00:00
- Duration
- 28.7 min
- Cost
- 36.35 USD billed
- Tokens
- 2.21M prompt · 2.09M completion · 4.30M total
z-ai/glm-5.3
mean on this sampled test
· 0.500 USD billed
· 24.9k / 119.8k / 144.7k tok
· 4.4 s / question
79.1
x-ai/grok-4.3
mean on this sampled test
· 0.306 USD billed
· 56.7k / 108.6k / 165.3k tok
· 5.5 s / question
94.4
x-ai/grok-4.5
mean on this sampled test
· 1.14 USD billed
· 59.7k / 175.8k / 235.4k tok
· 9.5 s / question
94.4
qwen/qwen3.7-max
mean on this sampled test
· 0.878 USD billed
· 26.1k / 189.7k / 215.8k tok
· 12.1 s / question
89.3
qwen/qwen3.7-plus
mean on this sampled test
· 0.250 USD billed
· 26.1k / 188.7k / 214.8k tok
· 13.5 s / question
90.9
openai/gpt-5.5-pro
mean on this sampled test
· 17.92 USD billed
· 23.4k / 95.6k / 119.0k tok
· 13.2 s / question
80.9
meta/muse-spark-1.3
mean on this sampled test
· 0.933 USD billed
· 26.9k / 211.6k / 238.4k tok
· 10.1 s / question
69.2
openai/gpt-5.6-sol-pro
mean on this sampled test
· 2.09 USD billed
· 452.7k / 118.5k / 571.3k tok
· 6.6 s / question
94.8
openai/gpt-6-astra-pro
mean on this sampled test
· 6.26 USD billed
· 368.2k / 51.6k / 419.8k tok
· 5.6 s / question
92.4
qwen/qwen3.8-2.4t-a95b
mean on this sampled test
· 0.917 USD billed
· 33.0k / 142.2k / 175.1k tok
· 7.6 s / question
70.2
openai/gpt-5.6-luna-pro
mean on this sampled test
· 0.311 USD billed
· 490.7k / 177.3k / 667.9k tok
· 6.6 s / question
96.2
deepseek/deepseek-v4-pro
mean on this sampled test
· 0.327 USD billed
· 26.3k / 123.8k / 150.1k tok
· 10.0 s / question
83.9
openai/gpt-5.6-terra-pro
mean on this sampled test
· 2.49 USD billed
· 460.9k / 130.7k / 591.7k tok
· 8.0 s / question
93.6
anthropic/claude-opus-4.7
mean on this sampled test
· 0.672 USD billed
· 36.4k / 19.6k / 56.0k tok
· 1.7 s / question
94.0
anthropic/claude-opus-4.8
mean on this sampled test
· 0.946 USD billed
· 35.7k / 30.7k / 66.4k tok
· 2.8 s / question
94.6
deepseek/deepseek-v4.1-flash
mean on this sampled test
· 0.104 USD billed
· 28.0k / 102.3k / 130.3k tok
· 5.4 s / question
75.5
deepseek/deepseek-v4-pro-0813
mean on this sampled test
· 0.307 USD billed
· 32.4k / 103.9k / 136.3k tok
· 6.7 s / question
78.3