Unverified50% confidenceBenchmarkExact time
OpenAI announced that Astra achieved 98% on Frontier Math Tier 4.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/17/2026
First Seen
Valid until: 12/16/2026
Sources
Related Entities
Related Claims
UnverifiedCiting a third-party programming benchmark, OpenAI states that Sol scored 80 points, 2.8 points higher than Claude's comparable model.64% similarUnverifiedFrontier Math Tier 4 went from a top score of under 5% at launch to a top score of 98% in under 14 months, leading Epoch to conclude that the benchmark has been saturated.62% similarUnverifiedOn the math reasoning task GSM8K, OQ4E answered 954 questions correctly (95.4%), while 8-bit only answered 924 correctly (92.4%), with the 4-bit version coming out 3 percentage points higher.56% similarUnverifiedIn front-end and visual tasks (Three.js, SVG, etc.), Sol scores only 6 to 7, while Fable 5 consistently scores 9 to 10, indicating that front-end remains a weak area for OpenAI.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/929036API
curl https://kongchang.com/api/v1/knowledge/claims/929036MCP
get_claim(id=929036)