99.0
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- wave5-5301
- Model
- openai/gpt-5.6-luna-pro
- Questions asked
- 177
- Seed
- 5301
- Fingerprint
- 6f22de71a9c74cfeeef1ad87
- When
- 2026-09-18T14:46:28.944570+00:00
- Duration
- 44.0 min
- Cost
- 37.16 USD billed
- Tokens
- 2.23M prompt · 2.09M completion · 4.32M total
z-ai/glm-5.3
mean on this sampled test
· 0.551 USD billed
· 24.9k / 130.2k / 155.1k tok
· 5.1 s / question
81.3
x-ai/grok-4.3
mean on this sampled test
· 0.311 USD billed
· 56.6k / 110.4k / 167.0k tok
· 5.5 s / question
97.0
x-ai/grok-4.5
mean on this sampled test
· 1.18 USD billed
· 59.5k / 182.2k / 241.8k tok
· 9.4 s / question
96.8
qwen/qwen3.7-max
mean on this sampled test
· 0.844 USD billed
· 26.2k / 182.0k / 208.2k tok
· 10.8 s / question
91.4
qwen/qwen3.7-plus
mean on this sampled test
· 0.236 USD billed
· 26.2k / 178.0k / 204.2k tok
· 12.7 s / question
91.6
openai/gpt-5.5-pro
mean on this sampled test
· 18.36 USD billed
· 24.2k / 98.0k / 122.2k tok
· 14.5 s / question
84.1
meta/muse-spark-1.3
mean on this sampled test
· 0.925 USD billed
· 26.7k / 209.8k / 236.6k tok
· 9.1 s / question
71.9
openai/gpt-5.6-sol-pro
mean on this sampled test
· 2.14 USD billed
· 457.6k / 122.6k / 580.2k tok
· 6.9 s / question
98.4
openai/gpt-6-astra-pro
mean on this sampled test
· 6.40 USD billed
· 371.9k / 53.7k / 425.6k tok
· 5.6 s / question
96.0
qwen/qwen3.8-2.4t-a95b
mean on this sampled test
· 0.899 USD billed
· 32.9k / 139.1k / 172.0k tok
· 6.3 s / question
70.7
openai/gpt-5.6-luna-pro
mean on this sampled test
· 0.321 USD billed
· 497.5k / 184.8k / 682.3k tok
· 7.2 s / question
99.0
deepseek/deepseek-v4-pro
mean on this sampled test
· 0.294 USD billed
· 26.5k / 110.7k / 137.2k tok
· 9.3 s / question
88.0
openai/gpt-5.6-terra-pro
mean on this sampled test
· 2.62 USD billed
· 469.5k / 139.7k / 609.2k tok
· 8.3 s / question
97.2
anthropic/claude-opus-4.7
mean on this sampled test
· 0.708 USD billed
· 36.3k / 21.1k / 57.4k tok
· 1.8 s / question
97.8
anthropic/claude-opus-4.8
mean on this sampled test
· 0.974 USD billed
· 35.4k / 31.9k / 67.3k tok
· 2.8 s / question
97.4
deepseek/deepseek-v4.1-flash
mean on this sampled test
· 0.110 USD billed
· 27.9k / 105.6k / 133.5k tok
· 4.7 s / question
76.9
deepseek/deepseek-v4-pro-0813
mean on this sampled test
· 0.284 USD billed
· 30.8k / 87.1k / 117.9k tok
· 7.1 s / question
81.9