Preseason
MatchesRankingsPrompts
GitHub
Preseason
MatchesRankingsPromptsMethodologyContact

© 2026 Preseason. All rights reserved.

PrivacyTerms
@betocmn
LLM Evals
Methodology

Arize Phoenix vs LlamaIndex

Arize PhoenixARArize PhoenixvsLLLlamaIndex
Arize PhoenixLlamaIndex
47%
53%

Leading: LlamaIndex (52.8%)

Statistics

MetricValue
Arize Phoenix wins34
LlamaIndex wins38
Abstains (no tool)194
Other tool chosen3671
Decisive cases72
Arize Phoenix win rate (unweighted)47.2%
95% CI36.1% - 58.6%
Arize Phoenix win rate (weighted)47.2%

Comments

Arize Phoenix

No comments yet

Verified critics can leave comments here.

LlamaIndex

No comments yet

Verified critics can leave comments here.

Per-model breakdown

ModelTierArize PhoenixLlamaIndexNoneOtherA rate
Llama 4 ScoutSmall338231257%
Qwen3 Coder NextMid1404185100%
GPT 5.4 MiniMid608193100%
MiniMax M2.7Frontier505113100%
Mistral Small 4Mid503188100%
Gemini 3.5 FlashSmall10875100%
Claude Haiku 4.5Small004196n/a
Claude Opus 4.6Frontier000126n/a
Claude Opus 4.8Frontier00776n/a
Claude Sonnet 4.6Frontier007203n/a
DeepSeek R1 0528Frontier0010200n/a
DeepSeek V3.2Mid0022101n/a
DeepSeek V4 FlashMid00479n/a
DeepSeek V4 ProFrontier00282n/a
Devstral 2 2512Mid0014158n/a
Gemini 2.5 FlashSmall001120n/a
Gemini 2.5 ProFrontier009199n/a
GLM 5 TurboFrontier0019107n/a
GLM 5.2Frontier00084n/a
GPT 5.3 CodexFrontier000210n/a
GPT 5.4Frontier000126n/a
GPT 5.5Frontier00381n/a
Kimi K2.5Frontier003111n/a
Kimi K2.7 CodeFrontier00182n/a
Llama 4 MaverickFrontier0014181n/a
MiMo V2 ProFrontier008118n/a
MiMo V2.5 ProFrontier00974n/a
MiniMax M3Frontier00678n/a

Per-prompt breakdown

PromptTierArize PhoenixLlamaIndexNoneOtherA rate
ai-support-agent-platformBeginner877543853%
ai-revenue-ops-copilotBeginner751150258%
ai-revenue-ops-copilotIntermediate57450742%
ai-support-agent-platformIntermediate37550730%
ai-revenue-ops-copilotAdvanced53250663%
ai-support-agent-platformAdvanced0755150%
ai-engineering-workflowAdvanced301126100%
ai-engineering-workflowIntermediate201128100%
ai-agent-applicationAdvanced11012950%
ai-agent-applicationIntermediate0111300%
ai-agent-applicationBeginner0028110n/a
ai-engineering-workflowBeginner006173n/a