96.6
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- wave6-5420
- Model
- x-ai/grok-4.6
- Questions asked
- 177
- Seed
- 5420
- Fingerprint
- d17d81db608a1bc8938bfd37
- When
- 2026-09-18T21:46:43.953391+00:00
- Duration
- 2.4 min
- Cost
- 3.18 USD billed
- Tokens
- 275.9k prompt · 907.5k completion · 1.18M total
x-ai/grok-4.6
mean on this sampled test
· 1.60 USD billed
· 59.5k / 252.1k / 311.5k tok
· 12.0 s / question
96.6
cohere/command-a
mean on this sampled test
· 0.497 USD billed
· 23.7k / 43.7k / 67.4k tok
· 4.4 s / question
83.0
z-ai/glm-5.3-flash
mean on this sampled test
· 0.063 USD billed
· 24.8k / 125.4k / 150.2k tok
· 6.6 s / question
84.8
amazon/nova-premier-v1
mean on this sampled test
· 0.032 USD billed
· 1.0k / 2.4k / 3.4k tok
· 39.3 s / question
1.6
mistralai/devstral-2512
mean on this sampled test
· 0.126 USD billed
· 26.6k / 58.0k / 84.6k tok
· 1.5 s / question
81.2
mistralai/codestral-2508
mean on this sampled test
· 0.045 USD billed
· 24.5k / 42.0k / 66.5k tok
· 1.9 s / question
77.0
thinkingmachines/inkling
mean on this sampled test
· 0.458 USD billed
· 25.4k / 107.1k / 132.5k tok
· 9.4 s / question
87.5
meta-llama/llama-4-maverick
mean on this sampled test
· 0.066 USD billed
· 24.9k / 78.4k / 103.3k tok
· 6.0 s / question
77.8
mistralai/mistral-medium-3.1
mean on this sampled test
· 0.126 USD billed
· 26.6k / 57.6k / 84.2k tok
· 1.6 s / question
85.3
mistralai/mistral-small-2603
mean on this sampled test
· 0.018 USD billed
· 13.3k / 27.1k / 40.5k tok
· 39.3 s / question
27.7
thinkingmachines/inkling-small
mean on this sampled test
· 0.149 USD billed
· 25.5k / 113.7k / 139.2k tok
· 2.4 s / question
79.8