98.2
The large value shows the leading mean for this attempt. Rankings are calculated across repeated attempts rather than from this result alone.
- Attempt
- wave4-5204
- Model
- openai/gpt-5.6-sol
- Questions asked
- 177
- Seed
- 5204
- Fingerprint
- 0876a55582c27d6dbfc5b038
- When
- 2026-09-18T10:55:39.544006+00:00
- Duration
- 7.8 min
- Cost
- 6.24 USD billed
- Tokens
- 169.9k prompt · 333.7k completion · 503.6k total
openai/gpt-5.5
93.9
openai/gpt-5.6-sol
98.2
openai/gpt-5.6-luna
94.1
openai/gpt-5.6-terra
96.2
anthropic/claude-opus-5
84.8
anthropic/claude-sonnet-5
94.3