Expired50% confidenceFactExact time
The median output token count per problem-solving attempt for Opus 4.7 is 60,000, while GPT 5.5 requires only 16,000.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/30/2026(expired)
Sources
DeepSWE Benchmark Reveals the Truth: GPT 5.5 Leads Opus 4.7 by a Wide Margin
bilibili7k的每日搬运5/29/2026
Related Claims
UnverifiedEarly GPT-4 had a pass rate of only 1.7% on SWE-bench, Claude 3 Opus approximately 4.8%, and it was not until mid-2024 that the 20% mark was surpassed.79% similarPartially VerifiedClaude Opus 4.8 scored 69.2% on the SWE-bench benchmark, compared to 58.6% for GPT 5.5 and 54.2% for Google Gemini.79% similarUnverifiedOpus 4.7 showed a significant regression in long-context (500K–1M token) retrieval, far underperforming DeepSeek and GPT 5.5.79% similarUnverifiedIn the Agents' Last Exam benchmark, GPT-5.6 Sol achieved a score of 53.6, which is 13.1 points higher than Claude Fable 5 using adaptive reasoning.75% similarUnverifiedClaude Opus 5在智能体搜索BrowseComp上得分30.8%，与GPT系列基本持平；工具增强多学科推理64.7%；生物学人类可解问题上高达90.1%75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/47588API
curl https://kongchang.com/api/v1/knowledge/claims/47588MCP
get_claim(id=47588)