Unverified50% confidenceBenchmarkExact time
Opus 5 achieved a 26% pass rate on the enterprise automation benchmark, higher than Fable's 17.4%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/9/2026
First Seen
Valid until: 12/8/2026
Sources
Related Entities
Related Claims
Unverified在Automation Bench上Claude Opus 5拿到约25%通过率，而其他模型普遍聚集在15%左右79% similarUnverifiedThe previous-generation Claude OPUS had a success rate of only 1.4% on a certain high-difficulty leaderboard, whereas Fable 5 reached approximately 30%, an improvement of more than 20 times.72% similarUnverifiedOpus 5's pass rate at Low Effort is approximately 60%, surpassing Opus 4.8's 59% at the Max level, for which the per-task cost is as high as $13.71% similarUnverifiedClaude 5.1's score on the commercial automation benchmark improved from 17.1% to 31.4%.70% similarUnverifiedThe median output token count per problem-solving attempt for Opus 4.7 is 60,000, while GPT 5.5 requires only 16,000.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/884554API
curl https://kongchang.com/api/v1/knowledge/claims/884554MCP
get_claim(id=884554)