Unverified50% confidenceFactExact time
The evaluation method described in the official guide is a lightweight performance test, with the core focus on the endpoint's response behavior rather than model quality, and the measurable metrics include single-request latency, throughput under batch requests, and whether the endpoint can stably return results.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
Unverified性能测试属于非功能性测试，通常需在SLA中预先定义响应时间和吞吐量等性能阈值作为判断基准77% similarUnverifiedThe focus of evaluation is shifting from the quality of model text output to the ability of agents to complete end-to-end tasks, with evaluation dimensions expanding from a single accuracy metric to multi-dimensional metrics including task completion rate, step efficiency, error recovery capability, and time overhead.77% similarUnverifiedEvaluating performance claims should focus on test transparency, reproducibility, end-to-end metrics (such as P50/P99 latency and time-to-first-token), and cost comparisons.74% similarUnverifiedWhen evaluating official performance claims, attention should be paid to the benchmark version used for comparison, the evaluation subset used, and whether the dedicated models were fine-tuned at an equivalent scale.74% similarUnverifiedIn this benchmark, each response contains two parts: a <think> block recording the model's stated reasoning process, and a <final> block specifying the action it intends to execute; a judge model first evaluates the final action, assigning labels such as SHORTCUT, HONEST_FAIL, and LEGIT_ESCALATION, with the reasoning trace serving as supporting evidence rather than the sole basis for judgment.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1027685API
curl https://kongchang.com/api/v1/knowledge/claims/1027685MCP
get_claim(id=1027685)