98.8
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- wave6-5423
- Model
- x-ai/grok-4.6
- Questions asked
- 177
- Seed
- 5423
- Fingerprint
- 5405352344815f8effa9a0d2
- When
- 2026-09-18T21:52:18.538956+00:00
- Duration
- 2.2 min
- Cost
- 2.98 USD billed
- Tokens
- 276.1k prompt · 861.8k completion · 1.14M total
x-ai/grok-4.6
mean on this sampled test
· 1.49 USD billed
· 59.5k / 232.9k / 292.4k tok
· 11.7 s / question
98.8
cohere/command-a
mean on this sampled test
· 0.487 USD billed
· 23.8k / 42.7k / 66.5k tok
· 4.5 s / question
86.3
z-ai/glm-5.3-flash
mean on this sampled test
· 0.063 USD billed
· 24.9k / 127.4k / 152.3k tok
· 6.5 s / question
88.3
amazon/nova-premier-v1
mean on this sampled test
· 0.035 USD billed
· 1.1k / 2.6k / 3.6k tok
· 39.3 s / question
2.2
mistralai/devstral-2512
mean on this sampled test
· 0.122 USD billed
· 26.7k / 55.7k / 82.4k tok
· 1.5 s / question
85.1
mistralai/codestral-2508
mean on this sampled test
· 0.046 USD billed
· 24.6k / 42.7k / 67.3k tok
· 1.8 s / question
81.8
thinkingmachines/inkling
mean on this sampled test
· 0.397 USD billed
· 25.5k / 92.0k / 117.5k tok
· 5.9 s / question
91.7
meta-llama/llama-4-maverick
mean on this sampled test
· 0.068 USD billed
· 24.9k / 81.9k / 106.9k tok
· 6.1 s / question
80.2
mistralai/mistral-medium-3.1
mean on this sampled test
· 0.121 USD billed
· 26.7k / 55.3k / 82.1k tok
· 1.5 s / question
87.7
mistralai/mistral-small-2603
mean on this sampled test
· 0.017 USD billed
· 12.7k / 25.4k / 38.2k tok
· 39.3 s / question
26.1
thinkingmachines/inkling-small
mean on this sampled test
· 0.136 USD billed
· 25.5k / 103.3k / 128.8k tok
· 2.3 s / question
85.3