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
- wave4-5202
- Model
- openai/gpt-5.6-sol
- Questions asked
- 177
- Seed
- 5202
- Fingerprint
- 7602cc939f2aec15506b0cd3
- When
- 2026-09-18T10:36:12.159677+00:00
- Duration
- 11.8 min
- Cost
- 6.31 USD billed
- Tokens
- 168.4k prompt · 338.1k completion · 506.5k total
openai/gpt-5.5
94.0
openai/gpt-5.6-sol
98.8
openai/gpt-5.6-luna
95.0
openai/gpt-5.6-terra
95.8
anthropic/claude-opus-5
85.1
anthropic/claude-sonnet-5
93.2