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
- wave4-5205
- Model
- openai/gpt-5.6-sol
- Questions asked
- 177
- Seed
- 5205
- Fingerprint
- 0db77e2f9e6fb81778aa8713
- When
- 2026-09-18T11:01:55.373804+00:00
- Duration
- 6.3 min
- Cost
- 6.22 USD billed
- Tokens
- 169.2k prompt · 335.0k completion · 504.2k total
openai/gpt-5.5
94.4
openai/gpt-5.6-sol
98.2
openai/gpt-5.6-luna
94.2
openai/gpt-5.6-terra
96.8
anthropic/claude-opus-5
85.1
anthropic/claude-sonnet-5
93.4