97.4
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- wave6-5425
- Model
- x-ai/grok-4.6
- Questions asked
- 177
- Seed
- 5425
- Fingerprint
- ccdceea6fdcc729c64e31faa
- When
- 2026-09-18T21:54:38.509657+00:00
- Duration
- 79.2 s
- Cost
- 2.85 USD billed
- Tokens
- 277.0k prompt · 838.6k completion · 1.12M total
x-ai/grok-4.6
mean on this sampled test
· 1.36 USD billed
· 59.5k / 212.6k / 272.1k tok
· 11.2 s / question
97.4
cohere/command-a
mean on this sampled test
· 0.468 USD billed
· 23.7k / 40.9k / 64.6k tok
· 4.2 s / question
82.7
z-ai/glm-5.3-flash
mean on this sampled test
· 0.064 USD billed
· 24.9k / 127.4k / 152.3k tok
· 6.8 s / question
86.7
amazon/nova-premier-v1
mean on this sampled test
· 0.033 USD billed
· 1.1k / 2.4k / 3.5k tok
· 39.3 s / question
1.6
mistralai/devstral-2512
mean on this sampled test
· 0.120 USD billed
· 26.7k / 54.5k / 81.2k tok
· 1.6 s / question
83.5
mistralai/codestral-2508
mean on this sampled test
· 0.041 USD billed
· 24.6k / 37.7k / 62.3k tok
· 1.6 s / question
80.1
thinkingmachines/inkling
mean on this sampled test
· 0.412 USD billed
· 25.5k / 95.6k / 121.0k tok
· 6.2 s / question
88.7
meta-llama/llama-4-maverick
mean on this sampled test
· 0.066 USD billed
· 24.9k / 78.2k / 103.1k tok
· 6.0 s / question
79.7
mistralai/mistral-medium-3.1
mean on this sampled test
· 0.119 USD billed
· 26.7k / 54.3k / 81.0k tok
· 1.6 s / question
86.5
mistralai/mistral-small-2603
mean on this sampled test
· 0.018 USD billed
· 14.1k / 26.8k / 41.0k tok
· 39.2 s / question
28.0
thinkingmachines/inkling-small
mean on this sampled test
· 0.142 USD billed
· 25.5k / 108.2k / 133.7k tok
· 2.1 s / question
82.1