97.8
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- wave8-5601
- Model
- x-ai/grok-4.6
- Questions asked
- 208
- Seed
- 5601
- Fingerprint
- cf1171b4d7b8b63304ac6617
- When
- 2026-09-19T10:34:57.141248+00:00
- Duration
- 26.8 min
- Cost
- 5.93 USD billed
- Tokens
- 222.6k prompt · 888.2k completion · 1.11M total
z-ai/glm-5.3
82.2
x-ai/grok-4.6
97.8
moonshotai/kimi-k3
88.8
qwen/qwen3.8-max-0902
67.4
deepseek/deepseek-v4-pro-0813
74.2