88.3
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- wave14-6107
- Model
- openai/gpt-6-luna-pro
- Questions asked
- 132
- Seed
- 6107
- Fingerprint
- e4da12768eacc57987df7570
- When
- 2026-10-06T20:16:54.413779+00:00
- Duration
- 6.3 min
- Cost
- 9.65 USD billed
- Tokens
- 1.14M prompt · 1.33M completion · 2.47M total
x-ai/grok-4.20
mean on this sampled test
· 0.124 USD billed
· 42.0k / 38.1k / 80.1k tok
· 2.8 s / question
84.1
fireworks/ember-1
mean on this sampled test
· 1.38 USD billed
· 30.8k / 85.5k / 116.3k tok
· 7.8 s / question
85.6
z-ai/glm-5.3-prime
mean on this sampled test
· 1.27 USD billed
· 19.4k / 138.0k / 157.4k tok
· 9.4 s / question
49.2
openai/gpt-6-sol-pro
mean on this sampled test
· 1.15 USD billed
· 285.5k / 57.9k / 343.4k tok
· 5.0 s / question
86.4
cohere/command-a-plus
mean on this sampled test
· 0.274 USD billed
· 17.1k / 179.1k / 196.3k tok
· 10.7 s / question
47.7
meta/muse-glimmer-30b
mean on this sampled test
· 0.182 USD billed
· 21.1k / 136.7k / 157.8k tok
· 16.2 s / question
51.9
openai/gpt-6-luna-pro
mean on this sampled test
· 0.088 USD billed
· 323.8k / 112.2k / 435.9k tok
· 6.6 s / question
88.3
qwen/qwen3.8-max-0902
mean on this sampled test
· 0.758 USD billed
· 25.3k / 118.0k / 143.3k tok
· 10.6 s / question
54.5
openai/gpt-6.1-sol-pro
mean on this sampled test
· 1.08 USD billed
· 289.1k / 50.4k / 339.5k tok
· 6.7 s / question
85.2
qwen/qwen3.8-max-prime
mean on this sampled test
· 1.56 USD billed
· 25.3k / 121.9k / 147.3k tok
· 6.4 s / question
49.6
xiaomi/mimo-v2.6-flash
mean on this sampled test
· 0.030 USD billed
· 19.3k / 94.9k / 114.3k tok
· 14.4 s / question
73.1
mistralai/mistral-medium-3-5
mean on this sampled test
· 0.456 USD billed
· 20.8k / 56.7k / 77.5k tok
· 1.7 s / question
74.6
xiaomi/mimo-v2.6-pro-ultraspeed
mean on this sampled test
· 1.30 USD billed
· 19.3k / 139.7k / 159.0k tok
· 4.3 s / question
58.0