Benchmark
Epoch AI evaluates GPT-5.6 Luna (low)
FrontierMath-Tiers-1-3-v2-Private 41.4%
- Type
- BENCHMARK_RESULT
- Detection
- benchmark
- Confidence
- high
- Status
Related entities
FrontierMath-Tiers-1-3-v2-Private 41.4%
Independent benchmark runs (GPQA Diamond, SWE-bench Verified, FrontierMath, ...) plus externally reported leaderboards and the Epoch Capabilities Index (ECI).