Thunderdome B2B SaaS AI Perception Index

← LLM & Agent Evals ranking

Brand report · September 2026

Ragas Ragas: AI Visibility Report

ragas.io ↗

When buyers ask ChatGPT, Claude, and Gemini about llm & agent evals, Ragas ranks #8 of 15, a Visibility Score of 21 in LLM & Agent Evals .

These rankings are measured from what the three models know from training, not a live web search. The live-web grounded surface is rolling out across the index. Methodology.

How AI sees Ragas

Ragas lives and dies in one arena, and it's losing.

Where it wins. A 33% mention rate in LLM & Agent Evals keeps Ragas in the conversation among 15 competitors, and its strongest foothold is with startup and small teams where eval budgets and tooling choices are still fluid.

Where it loses. Rank 8 of 15 with zero first-pick selections means buyers hear the name but route their trust elsewhere, and the complete absence from Feature-led ask prompts suggests Ragas cannot yet articulate a product capability story that stands on its own.

AI-generated analysis of the September 2026 measurements.

LLM & Agent Evals · #8 of 15

21 / 100 first snapshot (September 2026)
33%
mention rate (72 answers)
5
avg. position
0%
first pick
6%
share of voice
First snapshot: September 2026. The trend line appears with the second monthly measurement; no modeled history.
ChatGPT
5
Claude
29
Gemini
28

One of the index's bigger model splits: see where the models disagree →

How the models portray Ragas

Being named is not the same as being recommended. Each mention is graded endorsed (a strong pick), listed (a neutral option), or caveated (named with a reservation).

33% 42% 25%
endorsed · 95% band 18–53% listed caveated graded across 24 mentions in LLM & Agent Evals answers
Prompt themes Ragas would want to own

Share of each theme's answers that mention Ragas. Hover a row for the exact prompt. Compare shapes on the head-to-head page.

Gaps Feature-led ask

Most co-mentioned competitors

Share of Ragas's mentions where the AI models name this brand in the same answer. That is the real competitive set in the AI channel.

LangSmith
100%
Promptfoo
79%
DeepEval
54%
Braintrust
54%
Weights & Biases
50%
Arize Phoenix
50%

Scores are measured from real AI answers, refreshed monthly. Methodology.

Get alerted on big movements

We rerun the index every month. Drop your email and pick what to watch in LLM & Agent Evals: the whole category or specific brands. Free, unsubscribe anytime.

Or watch specific brands:

Work at Ragas? Put this on your site: a live "AI-recommended" badge, grounded in this data, that updates monthly and links back here. Free. Get the badge →