72.5
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- flash-2012
- Model
- google/gemini-3-flash-preview
- Questions asked
- 101
- Seed
- 2012
- Fingerprint
- 0d93b62f07d6a2fd1d210c27
- When
- 2026-09-07T02:54:54.809374+00:00
- Duration
- 28.2 min
- Cost
- 2.85 USD billed
- Tokens
- 177.9k prompt · 1.35M completion · 1.53M total
moonshotai/kimi-k2
mean on this sampled test
· 0.123 USD billed
· 9.6k / 51.0k / 60.5k tok
· 13.6 s / question
67.9
qwen/qwen3.6-flash
mean on this sampled test
· 0.156 USD billed
· 10.4k / 137.1k / 147.5k tok
· 15.2 s / question
55.7
qwen/qwen3.7-flash
mean on this sampled test
· 0.021 USD billed
· 10.7k / 157.7k / 168.3k tok
· 24.2 s / question
53.4
qwen/qwen3.8-flash
mean on this sampled test
· 0.029 USD billed
· 12.8k / 57.7k / 70.4k tok
· 17.3 s / question
63.4
moonshotai/kimi-k2.5
mean on this sampled test
· 0.461 USD billed
· 9.4k / 196.8k / 206.2k tok
· 62.4 s / question
67.2
moonshotai/kimi-k2.6
mean on this sampled test
· 0.363 USD billed
· 9.5k / 105.9k / 115.4k tok
· 36.3 s / question
61.1
google/gemini-2.5-flash
mean on this sampled test
· 0.103 USD billed
· 9.0k / 40.2k / 49.2k tok
· 4.8 s / question
64.9
google/gemini-3.5-flash
mean on this sampled test
· 0.721 USD billed
· 8.9k / 78.6k / 87.5k tok
· 8.3 s / question
64.1
google/gemini-3.6-flash
mean on this sampled test
· 0.292 USD billed
· 8.9k / 76.0k / 84.8k tok
· 8.3 s / question
61.8
google/gemini-3.7-flash
mean on this sampled test
· 0.142 USD billed
· 8.9k / 36.1k / 45.0k tok
· 5.3 s / question
67.9
google/gemini-3.8-flash
mean on this sampled test
· 0.188 USD billed
· 8.9k / 48.3k / 57.2k tok
· 5.6 s / question
66.4
qwen/qwen3.5-flash-02-23
mean on this sampled test
· 0.045 USD billed
· 10.7k / 171.6k / 182.3k tok
· 21.2 s / question
61.8
deepseek/deepseek-v4-flash
mean on this sampled test
· 0.0087 USD billed
· 9.9k / 28.9k / 38.8k tok
· 7.6 s / question
71.0
google/gemini-2.5-flash-lite
mean on this sampled test
· 0.019 USD billed
· 9.5k / 45.9k / 55.4k tok
· 2.2 s / question
64.9
google/gemini-3.1-flash-lite
mean on this sampled test
· 0.032 USD billed
· 9.1k / 19.7k / 28.8k tok
· 2.1 s / question
69.5
google/gemini-3.5-flash-lite
mean on this sampled test
· 0.059 USD billed
· 9.0k / 22.6k / 31.6k tok
· 1.9 s / question
65.6
google/gemini-3-flash-preview
mean on this sampled test
· 0.066 USD billed
· 9.0k / 20.6k / 29.6k tok
· 3.6 s / question
72.5
deepseek/deepseek-v4-flash-0731
mean on this sampled test
· 0.018 USD billed
· 14.0k / 55.4k / 69.4k tok
· 5.7 s / question
66.4