Unverified50% confidenceBenchmarkExact time
On the two benchmarks Earth-Bench and DisasterM3-Reason, OSGR with GPT-4o raised accuracy from 49.3% to 63.7%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/4/2026
First Seen
Valid until: 2/2/2027
Sources
Related Entities
Related Claims
UnverifiedAccording to the paper, GPT-4o achieves a baseline accuracy of 49.3% on the Earth-Bench benchmark.77% similarUnverifiedWhen paired with GPT-4o, FinDialogLens achieves 94.3% accuracy on trade outcome determination.70% similarUnverifiedThe study found that GPT-4's accuracy on the prime number identification task plummeted from 97.6% in March 2023 to 2.4% in June 2023.69% similarUnverifiedIn EvoArena testing, GPT-5.5, which achieved the highest Step Level score, had an accuracy of just over 50%, while Gemini-3.1 Pro and GLM-5.1, which performed best at the Chain Level, reached only approximately 28%–29%.69% similarUnverifiedIn Automation Bench at medium reasoning intensity, GPT-6.1 Sol scored 35.4%, which is 2.2 percentage points higher than Opus 5.5 at one-third of the cost.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1133992API
curl https://kongchang.com/api/v1/knowledge/claims/1133992MCP
get_claim(id=1133992)