92.8
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- wave15-6202
- Model
- openai/gpt-4.1-mini
- Questions asked
- 132
- Seed
- 6202
- Fingerprint
- b0dbb4766d7ed28282f4a024
- When
- 2026-10-08T23:01:31.471238+00:00
- Duration
- 7.3 min
- Cost
- 2.03 USD billed
- Tokens
- 194.2k prompt · 656.2k completion · 850.4k total
openai/gpt-4.1
mean on this sampled test
· 0.362 USD billed
· 19.5k / 40.4k / 59.9k tok
· 2.6 s / question
84.5
qwen/qwen3.8-27b
mean on this sampled test
· 0.319 USD billed
· 26.4k / 132.4k / 158.8k tok
· 9.9 s / question
45.0
xiaomi/mimo-v2.5
mean on this sampled test
· 0.032 USD billed
· 19.8k / 87.4k / 107.1k tok
· 11.8 s / question
70.9
openai/gpt-4.1-mini
mean on this sampled test
· 0.074 USD billed
· 19.5k / 41.4k / 60.8k tok
· 2.7 s / question
92.8
openai/gpt-5.4-nano
mean on this sampled test
· 0.049 USD billed
· 19.3k / 36.3k / 55.7k tok
· 2.1 s / question
85.3
xiaomi/mimo-v2.5-pro
mean on this sampled test
· 0.105 USD billed
· 19.8k / 120.7k / 140.5k tok
· 18.2 s / question
73.7
anthropic/claude-sonnet-4
mean on this sampled test
· 1.01 USD billed
· 20.7k / 63.5k / 84.2k tok
· 5.1 s / question
91.4
anthropic/claude-haiku-5.5
mean on this sampled test
· 0.045 USD billed
· 28.5k / 84.9k / 113.4k tok
· 3.1 s / question
85.6
meta-llama/llama-3.3-70b-instruct
mean on this sampled test
· 0.030 USD billed
· 20.7k / 49.2k / 70.0k tok
· 9.1 s / question
73.0