97.5
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- wave5-5302
- Model
- openai/gpt-5.6-luna-pro
- Questions asked
- 177
- Seed
- 5302
- Fingerprint
- 1e877d0bb49f7193fbc05caf
- When
- 2026-09-18T15:25:17.281165+00:00
- Duration
- 8.8 min
- Cost
- 36.21 USD billed
- Tokens
- 2.20M prompt · 2.13M completion · 4.33M total
z-ai/glm-5.3
mean on this sampled test
· 0.549 USD billed
· 24.8k / 127.7k / 152.5k tok
· 6.0 s / question
84.0
x-ai/grok-4.3
mean on this sampled test
· 0.300 USD billed
· 56.5k / 106.2k / 162.7k tok
· 5.5 s / question
95.5
x-ai/grok-4.5
mean on this sampled test
· 1.14 USD billed
· 59.4k / 176.5k / 235.9k tok
· 9.4 s / question
96.1
qwen/qwen3.7-max
mean on this sampled test
· 0.873 USD billed
· 26.0k / 188.6k / 214.6k tok
· 11.5 s / question
91.8
qwen/qwen3.7-plus
mean on this sampled test
· 0.247 USD billed
· 26.0k / 186.5k / 212.5k tok
· 13.4 s / question
92.4
openai/gpt-5.5-pro
mean on this sampled test
· 17.47 USD billed
· 24.0k / 93.1k / 117.1k tok
· 12.6 s / question
82.1
meta/muse-spark-1.3
mean on this sampled test
· 0.921 USD billed
· 26.6k / 208.9k / 235.5k tok
· 10.6 s / question
74.1
openai/gpt-5.6-sol-pro
mean on this sampled test
· 2.02 USD billed
· 449.4k / 112.3k / 561.7k tok
· 6.5 s / question
96.7
openai/gpt-6-astra-pro
mean on this sampled test
· 6.24 USD billed
· 368.7k / 51.2k / 419.8k tok
· 5.7 s / question
94.5
qwen/qwen3.8-2.4t-a95b
mean on this sampled test
· 1.32 USD billed
· 32.7k / 209.5k / 242.2k tok
· 7.2 s / question
74.1
openai/gpt-5.6-luna-pro
mean on this sampled test
· 0.308 USD billed
· 487.0k / 175.2k / 662.3k tok
· 6.6 s / question
97.5
deepseek/deepseek-v4-pro
mean on this sampled test
· 0.315 USD billed
· 26.6k / 119.9k / 146.5k tok
· 9.2 s / question
88.3
openai/gpt-5.6-terra-pro
mean on this sampled test
· 2.48 USD billed
· 460.3k / 130.1k / 590.4k tok
· 7.6 s / question
95.9
anthropic/claude-opus-4.7
mean on this sampled test
· 0.662 USD billed
· 36.3k / 19.2k / 55.5k tok
· 2.0 s / question
96.9
anthropic/claude-opus-4.8
mean on this sampled test
· 0.942 USD billed
· 35.4k / 30.6k / 66.0k tok
· 2.8 s / question
96.3
deepseek/deepseek-v4.1-flash
mean on this sampled test
· 0.100 USD billed
· 27.7k / 97.2k / 124.9k tok
· 4.7 s / question
77.8
deepseek/deepseek-v4-pro-0813
mean on this sampled test
· 0.310 USD billed
· 31.4k / 102.1k / 133.5k tok
· 6.8 s / question
79.9