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
- flash-2005
- Model
- deepseek/deepseek-v4-flash
- Questions asked
- 101
- Seed
- 2005
- Fingerprint
- 2456f526de9b822384a952ea
- When
- 2026-09-06T21:41:46.429385+00:00
- Duration
- 43.4 min
- Cost
- 3.30 USD billed
- Tokens
- 235.3k prompt · 1.67M completion · 1.91M total
moonshotai/kimi-k2
mean on this sampled test
· 0.136 USD billed
· 12.2k / 56.1k / 68.3k tok
· 11.0 s / question
83.2
qwen/qwen3.6-flash
mean on this sampled test
· 0.224 USD billed
· 14.5k / 196.6k / 211.1k tok
· 11.1 s / question
74.8
qwen/qwen3.7-flash
mean on this sampled test
· 0.027 USD billed
· 15.2k / 204.6k / 219.8k tok
· 19.4 s / question
77.9
qwen/qwen3.8-flash
mean on this sampled test
· 0.033 USD billed
· 18.3k / 63.8k / 82.1k tok
· 7.2 s / question
86.3
moonshotai/kimi-k2.5
mean on this sampled test
· 0.558 USD billed
· 12.1k / 235.4k / 247.6k tok
· 43.6 s / question
80.9
moonshotai/kimi-k2.6
mean on this sampled test
· 0.467 USD billed
· 11.4k / 136.9k / 148.4k tok
· 23.7 s / question
69.5
google/gemini-2.5-flash
mean on this sampled test
· 0.107 USD billed
· 11.2k / 41.6k / 52.7k tok
· 3.7 s / question
77.1
google/gemini-3.5-flash
mean on this sampled test
· 0.739 USD billed
· 9.8k / 80.4k / 90.3k tok
· 7.7 s / question
71.8
google/gemini-3.6-flash
mean on this sampled test
· 0.308 USD billed
· 10.5k / 80.0k / 90.6k tok
· 7.3 s / question
73.3
google/gemini-3.7-flash
mean on this sampled test
· 0.170 USD billed
· 10.9k / 43.2k / 54.2k tok
· 5.4 s / question
80.2
google/gemini-3.8-flash
mean on this sampled test
· 0.223 USD billed
· 10.9k / 57.2k / 68.1k tok
· 4.4 s / question
79.4
qwen/qwen3.5-flash-02-23
mean on this sampled test
· 0.062 USD billed
· 15.2k / 233.4k / 248.6k tok
· 11.7 s / question
84.0
deepseek/deepseek-v4-flash
mean on this sampled test
· 0.012 USD billed
· 14.5k / 41.4k / 55.9k tok
· 4.8 s / question
94.7
google/gemini-2.5-flash-lite
mean on this sampled test
· 0.023 USD billed
· 13.5k / 54.6k / 68.2k tok
· 1.6 s / question
87.8
google/gemini-3.1-flash-lite
mean on this sampled test
· 0.042 USD billed
· 12.4k / 26.2k / 38.6k tok
· 1.7 s / question
88.5
google/gemini-3.5-flash-lite
mean on this sampled test
· 0.071 USD billed
· 11.5k / 27.1k / 38.6k tok
· 1.6 s / question
80.2
google/gemini-3-flash-preview
mean on this sampled test
· 0.081 USD billed
· 11.0k / 25.3k / 36.3k tok
· 3.4 s / question
84.7
deepseek/deepseek-v4-flash-0731
mean on this sampled test
· 0.015 USD billed
· 20.0k / 68.1k / 88.1k tok
· 3.2 s / question
88.5