G2 AI CX Agent Evaluations
Compare AI customer experience agents using evaluation criteria tailored to the workflows and requirements of each use case. Explore insights from G2's latest CX evaluation.
Agent Evaluation Score × G2 Market Presence Beta
See how each AI CX agent performed in G2’s evaluation alongside the Market Presence of its G2 product.
Agent coverage · 12 evaluated agents
| Evaluated agent / slug | Market-presence product / slug | Market presence / source category | Mapping |
|---|---|---|---|
| Retell AIretell-ai | 52.2AI CX Agents | Same product | |
| Yuma AIyuma-ai | 23.2AI Customer Support Agents | Same product | |
| LiveAgentliveagent | 25.4AI CX Agents | Assumed match | |
| Chippchipp | 5.0AI CX Agents | Assumed match | |
| Forethought AI Agentsforethought-ai-agents | 35.0AI CX Agents | Same product | |
| Tidiotidio | 58.7AI CX Agents | Assumed match | |
| BoldDeskbolddesk | 39.1AI CX Agents | Assumed match | |
| Zendesk for Customer Servicezendesk-for-customer-service | 96.0AI CX Agents | Assumed match | |
| Zoho Deskzoho-desk | 81.9AI CX Agents | Assumed match | |
| Jotform AI Agentsjotform-ai-agents | 73.4AI CX Agents | Same product | |
| HubSpot Service Hubhubspot-service-hub | 92.8AI CX Agents | Assumed match | |
| Freshchatfreshworks-freshchat | 46.0AI CX Agents | Assumed match |
Agent Evaluation Grid methodology
The Agent Evaluation Grid adapts G2’s existing Grid framework for Agent Evaluations. Unlike the standard G2 Grid, which compares products based on User Satisfaction and Market Presence, this Grid compares an agent’s Evaluation Score with the Market Presence of its corresponding G2 product.
In G2’s Customer Experience evaluation, every agent handles the same 50 buyer-informed support tasks in a simulated company with a written support policy and 38 working business tools. G2 configures each product as a customer would and records the full conversation and the actions the agent takes.
Agent Evaluation results don’t affect a product’s G2 Score, Market Presence, or Standard Grid placement.
Evaluation Score
The Evaluation Score is the percentage of task points an agent earned in G2’s Customer Experience evaluation. Each task is worth five points, with 250 points available across the current task set. Results are averaged across runs. For this evaluation grid, 235.7 out of 250 points is shown as an Evaluation Score of 94%.
Selecting an agent in the grid also shows its performance across four evaluation dimensions:
- Accuracy: Are the agent's claims supported by evidence?
- Policy compliance: Did the agent follow the written policy?
- Relevance: Did the agent stay focused on the customer's problem?
- Completeness: Did the required outcomes happen in the underlying systems?
These dimensions provide additional detail about the agent's performance and are reported separately from its Evaluation Score.
Market Presence
Market Presence combines metrics from G2 reviews and third-party sources to indicate the market presence of a product and its vendor. Review volume is weighted for quality, recency, and source.
Each evaluated agent is mapped to the closest available G2 product. Click on a product in the Grid to see its Market Presence score and a link to its corresponding G2 product profile.
Market Presence is calculated separately from the Agent Evaluation Score and is not a measure of agent performance or buyer satisfaction.
Forethought: Market Presence reflects the Forethought brand before its acquisition by Zendesk.
About these results
Agent Evaluations are currently in beta. Results are dated snapshots and may change as G2 refreshes evaluations and refines its methodology.