Benchmark30 Aug 2026 00:00 UTC · 30d ago

Epoch AI evaluates GPT-6 Astra

GPQA diamond 95.8% · FrontierMath-Tiers-1-3-v2-Private 93.7% · FrontierMath-Tier-4-v2-Private 97.6% · OTIS Mock AIME 2024-2025 100.0%

Type: BENCHMARK_RESULT
Detection: benchmark
Confidence: high
Status

Related entities

ModelGPT-6 Astra CompanyOpenAI

Primary source

Epoch AI Benchmarking Hub · epoch.ai/benchmarks ↗

Independent benchmark runs (GPQA Diamond, SWE-bench Verified, FrontierMath, ...) plus externally reported leaderboards and the Epoch Capabilities Index (ECI).

Related events

Benchmark19d ago
Epoch AI evaluates GPT-6 Astra
Epoch AI Benchmarking HubGPT-6 Astra OpenAI
Model launch26d ago
OpenAI releases GPT-6 Astra
Epoch AI Benchmarking HubGPT-6 Astra OpenAI