94.7
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- wave15-6203
- Model
- openai/gpt-4.1-mini
- Questions asked
- 132
- Seed
- 6203
- Fingerprint
- 38d6b898bce923b0eb5ec44a
- When
- 2026-10-08T23:08:16.751703+00:00
- Duration
- 6.7 min
- Cost
- 2.03 USD billed
- Tokens
- 192.5k prompt · 668.4k completion · 860.9k total
openai/gpt-4.1
mean on this sampled test
· 0.371 USD billed
· 19.3k / 41.6k / 60.8k tok
· 2.6 s / question
87.1
qwen/qwen3.8-27b
mean on this sampled test
· 0.329 USD billed
· 26.4k / 138.2k / 164.7k tok
· 13.9 s / question
47.7
xiaomi/mimo-v2.5
mean on this sampled test
· 0.032 USD billed
· 19.6k / 89.4k / 109.0k tok
· 11.8 s / question
71.6
openai/gpt-4.1-mini
mean on this sampled test
· 0.074 USD billed
· 19.3k / 41.5k / 60.7k tok
· 2.6 s / question
94.7
openai/gpt-5.4-nano
mean on this sampled test
· 0.046 USD billed
· 19.1k / 34.1k / 53.3k tok
· 1.9 s / question
86.7
xiaomi/mimo-v2.5-pro
mean on this sampled test
· 0.107 USD billed
· 19.6k / 126.4k / 145.9k tok
· 18.6 s / question
76.5
anthropic/claude-sonnet-4
mean on this sampled test
· 0.993 USD billed
· 20.5k / 62.1k / 82.6k tok
· 5.0 s / question
93.9
anthropic/claude-haiku-5.5
mean on this sampled test
· 0.046 USD billed
· 28.3k / 86.4k / 114.7k tok
· 3.1 s / question
86.7
meta-llama/llama-3.3-70b-instruct
mean on this sampled test
· 0.029 USD billed
· 20.5k / 48.6k / 69.1k tok
· 9.3 s / question
77.7