95.0
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- wave15-6201
- Model
- anthropic/claude-sonnet-4
- Questions asked
- 132
- Seed
- 6201
- Fingerprint
- 1c9a930c44fb71fcc23b4136
- When
- 2026-10-08T22:54:12.574754+00:00
- Duration
- 21.8 min
- Cost
- 2.03 USD billed
- Tokens
- 191.4k prompt · 672.9k completion · 864.3k total
openai/gpt-4.1
mean on this sampled test
· 0.371 USD billed
· 19.2k / 41.6k / 60.7k tok
· 2.6 s / question
85.1
qwen/qwen3.8-27b
mean on this sampled test
· 0.340 USD billed
· 26.1k / 140.8k / 166.9k tok
· 14.6 s / question
43.4
xiaomi/mimo-v2.5
mean on this sampled test
· 0.033 USD billed
· 19.5k / 91.8k / 111.3k tok
· 12.3 s / question
77.6
openai/gpt-4.1-mini
mean on this sampled test
· 0.073 USD billed
· 19.2k / 40.9k / 60.1k tok
· 2.6 s / question
94.3
openai/gpt-5.4-nano
mean on this sampled test
· 0.047 USD billed
· 19.0k / 34.8k / 53.8k tok
· 2.0 s / question
84.0
xiaomi/mimo-v2.5-pro
mean on this sampled test
· 0.111 USD billed
· 19.5k / 126.7k / 146.2k tok
· 17.5 s / question
78.3
anthropic/claude-sonnet-4
mean on this sampled test
· 0.980 USD billed
· 20.4k / 61.2k / 81.6k tok
· 5.1 s / question
95.0
anthropic/claude-haiku-5.5
mean on this sampled test
· 0.046 USD billed
· 28.1k / 86.1k / 114.1k tok
· 3.0 s / question
87.2
meta-llama/llama-3.3-70b-instruct
mean on this sampled test
· 0.031 USD billed
· 20.6k / 49.0k / 69.6k tok
· 12.0 s / question
76.2