Arena ranking
Browse Agent Tool Hallucination results, model ratings and supporting selection context.
Data as of 2026-11-07
This source leaderboard ranking orders models by their original Arena rank rather than an aggregated benchmark score.
Rank | Model | Source Agent score | LLMBoard Score | Observations | Official input / 1M | Output speed |
|---|
| Rank01 | ModelXA | Source Agent score0.89% | LLMBoard ScoreN/A | Observations3.6M | Official input / 1M$2 | Output speedN/A |
| Rank02 | ModelZA | Source Agent score0.89% | LLMBoard ScoreN/A | Observations11.9M | Official input / 1M$0.1195 | Output speed31.51 tok/s |
| Rank03 | ModelZA | Source Agent score0.89% | LLMBoard ScoreN/A | Observations10.2M | Official input / 1M$1.2 | Output speedN/A |
| Rank04 | ModelOP | Source Agent score0.89% | LLMBoard ScoreN/A | Observations2.7M | Official input / 1M$0.10 | Output speedN/A |
| Rank05 | ModelDE | Source Agent score0.89% | LLMBoard ScoreN/A | Observations812K | Official input / 1M$0.66 | Output speedN/A |
| Rank06 | ModelOP | Source Agent score0.89% | LLMBoard ScoreN/A | Observations1.2M | Official input / 1M$10 | Output speed48.60 tok/s |
| Rank07 | ModelOP | Source Agent score0.89% | LLMBoard ScoreN/A | Observations6.1M | Official input / 1M$4 | Output speedN/A |
| Rank08 | ModelMA | Source Agent score0.89% | LLMBoard ScoreN/A | Observations14.8M | Official input / 1M$3 | Output speedN/A |
| Rank09 | ModelXA | Source Agent score0.89% | LLMBoard ScoreN/A | Observations3.3M | Official input / 1M$2 | Output speedN/A |
| Rank10 | ModelZA | Source Agent score0.89% | LLMBoard ScoreN/A | Observations8.4M | Official input / 1M$1.2 | Output speedN/A |
| Rank11 | ModelOP | Source Agent score0.88% | LLMBoard ScoreN/A | Observations3.3M | Official input / 1M$2 | Output speedN/A |
| Rank12 | ModelME | Source Agent score0.85% | LLMBoard ScoreN/A | Observations7.7M | Official input / 1M$1.25 | Output speed80.95 tok/s |
| Rank13 | ModelME | Source Agent score0.84% | LLMBoard ScoreN/A | Observations7.8M | Official input / 1M$1.25 | Output speed3.62 tok/s |
| Rank14 | ModelAN | Source Agent score0.84% | LLMBoard ScoreN/A | Observations4.3M | Official input / 1M$5 | Output speedN/A |
| Rank15 | ModelAN | Source Agent score0.77% | LLMBoard ScoreN/A | Observations2.2M | Official input / 1M$10 | Output speedN/A |
| Rank16 | ModelME | Source Agent score0.72% | LLMBoard ScoreN/A | Observations3.3M | Official input / 1M$1.25 | Output speedN/A |
| Rank17 | ModelAN | Source Agent score0.61% | LLMBoard ScoreN/A | Observations3.1M | Official input / 1M$10 | Output speedN/A |
| Rank18 | ModelGO | Source Agent score0.58% | LLMBoard ScoreN/A | Observations5.6M | Official input / 1M$0.75 | Output speedN/A |
| Rank19 | ModelGO | Source Agent score0.51% | LLMBoard ScoreN/A | Observations6.7M | Official input / 1MN/A | Output speedN/A |
| Rank20 | ModelAN | Source Agent score0.51% | LLMBoard ScoreN/A | Observations4.8M | Official input / 1M$2 | Output speed42.00 tok/s |
| Rank21 | ModelGO | Source Agent score0.42% | LLMBoard ScoreN/A | Observations5.8M | Official input / 1M$2 | Output speedN/A |
| Rank22 | ModelGO | Source Agent score0.41% | LLMBoard ScoreN/A | Observations7.3M | Official input / 1M$0.75 | Output speed107.73 tok/s |
| Rank23 | ModelMI | Source Agent score0.26% | LLMBoard ScoreN/A | Observations2.2M | Official input / 1M$0.15 | Output speedN/A |
| Rank24 | ModelTE | Source Agent score0.09% | LLMBoard ScoreN/A | Observations10.1M | Official input / 1MN/A | Output speedN/A |
| Rank25 | ModelAC | Source Agent score0.08% | LLMBoard ScoreN/A | Observations7.8M | Official input / 1MN/A | Output speedN/A |
| Rank26 | ModelGO | Source Agent score-0.03% | LLMBoard ScoreN/A | Observations2.7M | Official input / 1M$2 | Output speed90.00 tok/s |
| Rank27 | ModelXI | Source Agent score-0.06% | LLMBoard ScoreN/A | Observations4.6M | Official input / 1M$0.435 | Output speed4.94 tok/s |
| Rank28 | ModelMA | Source Agent score-0.16% | LLMBoard ScoreN/A | Observations386.3K | Official input / 1M$0.70 | Output speed50.35 tok/s |
| Rank29 | ModelAC | Source Agent score-0.29% | LLMBoard ScoreN/A | Observations2.1M | Official input / 1M$2.5 | Output speedN/A |
| Rank30 | ModelAC | Source Agent score-0.73% | LLMBoard ScoreN/A | Observations7.3M | Official input / 1M$2 | Output speedN/A |
This leaderboard overview compares the source ranking, score gaps and observed task volume.
Use confidence and observed task volume to judge how firmly each leaderboard position is supported; these source proportions remain separate from benchmark coverage.
Vendor representation among the top-ranked models in this leaderboard.
A practical summary of the first five entries in this agent tool hallucination AI model leaderboard, with benchmark evidence and pricing kept in context.
Common questions about the Agent Tool Hallucination Leaderboard.
Grok 4.6 is currently ranked first with 0.89 Agent score.
The current leaders are Grok 4.6 (rank #1), GLM 5.3 Flash (rank #2), and GLM 5.3 (rank #3).
GPT-6-Luna has the lowest matched official input price at $0.1 per 1M tokens.
The fastest matched records are MiniMax M3 (156.78 tok/s via MiniMax), Gemini 3.8 Flash (107.73 tok/s via Google), and Gemini 3.1 Pro (90.00 tok/s via Google).
No. Source Arena results describe a particular task or preference signal. Capability benchmarks, prices and runtime can produce different rankings.
This source-native ranking follows the original source metric. Benchmark evidence is shown separately and is not substituted for the source result.
This page currently compares 44 models.
A model may not yet have a matching Arena result, or multiple version results may resolve to the same model.
Ranking basisThis agent tool hallucination AI model leaderboard uses the source agent score and rank. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
Selection summary
Grok 4.6 currently leads the agent tool hallucination ranking at 0.89%. Compare evidence coverage, source activity and price separately before choosing a model for production.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.