SAGE (Service Agent) - Telecom Package: leaderboard

SAGE overall assessment score in the telecom package customer-service scenario: telecom package billing and plan upgrades (linear SOP), combining procedure compliance and conversational quality on a 0-100 scale, higher is better. It is unrelated to the SAGE robustness benchmark.

Metric: Overall Assessment Score (0-100), 0.8 x logical compliance + 0.2 conversational quality, in the Telecom Package scenario (telecom package billing and plan upgrades (linear SOP)), over SAGE customer-service dialogues: standard operating procedures formalized as dialogue graphs, an adversarial simulated user with varied intents and personas, turns 1, 5, 10, 15 and the final turn scored; three unnamed judge LLMs (majority vote and mean) plus a deterministic rule engine produce the reference; closed models through their APIs, open models served with vLLM; 0-100 scale; higher is better. Source: arxiv.org. Saturation forecast: Around April 2028. 27 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Claude Sonnet 4.575.03#261
2Claude Opus 4.573.12#160
3DeepSeek V371.6#729
4DeepSeek V3.270.61#419
5DeepSeek R170.39#482
6MiniMax-M2.170.12#575
7Kimi K2.569.41#266
8Qwen 2.5 72B Instruct69.16#1117
9Gemini 3 Pro (Preview)69.09#119
10Qwen 2.5 32B Instruct68.27#1247
11Qwen 3 14B68.01#1269
12GPT-4.166.9#505
13Gemini 2.5 Pro66.42#276
14GLM-4.766.02#380
15Seed 1.865.89#252

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=sage-service-agent-telecom-package · How It Works · Data refreshed daily, snapshot 2026-11-21.