96.0
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- wave5-5305
- Model
- openai/gpt-5.6-luna-pro
- Questions asked
- 177
- Seed
- 5305
- Fingerprint
- c989010ea52bf1cae3a8ebd5
- When
- 2026-09-18T16:59:37.562277+00:00
- Duration
- 16.9 min
- Cost
- 38.38 USD billed
- Tokens
- 2.26M prompt · 2.14M completion · 4.40M total
z-ai/glm-5.3
mean on this sampled test
· 0.513 USD billed
· 25.0k / 120.3k / 145.3k tok
· 5.5 s / question
80.2
x-ai/grok-4.3
mean on this sampled test
· 0.305 USD billed
· 56.8k / 108.0k / 164.8k tok
· 5.7 s / question
93.2
x-ai/grok-4.5
mean on this sampled test
· 1.14 USD billed
· 59.8k / 176.0k / 235.8k tok
· 9.4 s / question
93.6
qwen/qwen3.7-max
mean on this sampled test
· 0.854 USD billed
· 26.2k / 184.3k / 210.5k tok
· 11.4 s / question
88.2
qwen/qwen3.7-plus
mean on this sampled test
· 0.240 USD billed
· 26.2k / 181.3k / 207.5k tok
· 13.4 s / question
90.2
openai/gpt-5.5-pro
mean on this sampled test
· 19.33 USD billed
· 24.1k / 103.3k / 127.5k tok
· 12.5 s / question
79.8
meta/muse-spark-1.3
mean on this sampled test
· 0.943 USD billed
· 26.9k / 213.9k / 240.9k tok
· 10.0 s / question
70.2
openai/gpt-5.6-sol-pro
mean on this sampled test
· 2.21 USD billed
· 465.3k / 128.4k / 593.7k tok
· 6.8 s / question
95.4
openai/gpt-6-astra-pro
mean on this sampled test
· 6.50 USD billed
· 373.8k / 55.3k / 429.1k tok
· 5.5 s / question
93.2
qwen/qwen3.8-2.4t-a95b
mean on this sampled test
· 0.874 USD billed
· 33.1k / 134.9k / 168.0k tok
· 7.6 s / question
69.6
openai/gpt-5.6-luna-pro
mean on this sampled test
· 0.335 USD billed
· 507.2k / 195.0k / 702.2k tok
· 6.4 s / question
96.0
deepseek/deepseek-v4-pro
mean on this sampled test
· 0.319 USD billed
· 27.1k / 122.7k / 149.9k tok
· 9.8 s / question
81.8
openai/gpt-5.6-terra-pro
mean on this sampled test
· 2.74 USD billed
· 478.0k / 148.9k / 626.9k tok
· 7.7 s / question
92.0
anthropic/claude-opus-4.7
mean on this sampled test
· 0.663 USD billed
· 36.5k / 19.2k / 55.7k tok
· 1.9 s / question
93.6
anthropic/claude-opus-4.8
mean on this sampled test
· 0.974 USD billed
· 35.8k / 31.8k / 67.6k tok
· 2.8 s / question
93.6
deepseek/deepseek-v4.1-flash
mean on this sampled test
· 0.112 USD billed
· 28.1k / 111.8k / 139.9k tok
· 4.0 s / question
75.4
deepseek/deepseek-v4-pro-0813
mean on this sampled test
· 0.317 USD billed
· 31.8k / 103.6k / 135.4k tok
· 6.4 s / question
78.2