Arena benchmark
LM Arena Agent Tool Hallucination Leaderboard
LM Arena Agent Tool Hallucination model ratings and results.
Updated Aug 17, 2026. Data as of 2026-08-17
Models40
Categories1
Result typeagent_score
Agent Tool Hallucination Ranking
Models are ordered by their Arena rank.
Sort by
Rank | Model | Organization | Rating / score | Votes | Observations | Result date |
|---|
| Rank01 | ModelOP | Organizationopenai | Rating / score0.0 | VotesN/A | Observations693.8K | Result date |
| Rank02 | ModelMA | Organizationmoonshot | Rating / score0.0 | VotesN/A | Observations2.3M | Result date |
| Rank03 | ModelOP | Organizationopenai | Rating / score0.0 | VotesN/A | Observations1.5M | Result date |
| Rank04 | ModelOP | Organizationopenai | Rating / score0.0 | VotesN/A | Observations2.9M | Result date |
| Rank05 | ModelXA | Organizationxai | Rating / score0.0 | VotesN/A | Observations1.3M | Result date |
| Rank06 | ModelZA | Organizationzai | Rating / score0.0 | VotesN/A | Observations2.2M | Result date |
| Rank07 | ModelOP | Organizationopenai | Rating / score0.0 | VotesN/A | Observations1.5M | Result date |
| Rank09 | ModelOP | Organizationopenai | Rating / score0.0 | VotesN/A | Observations496.9K | Result date |
| Rank10 | ModelMA | Organizationmoonshot | Rating / score0.0 | VotesN/A | Observations297.2K | Result date |
| Rank11 | ModelMA | Organizationmoonshot | Rating / score0.0 | VotesN/A | Observations375.3K | Result date |
| Rank12 | ModelAN | Organizationanthropic | Rating / score0.0 | VotesN/A | Observations853.8K | Result date |
| Rank13 | ModelAN | Organizationanthropic | Rating / score0.0 | VotesN/A | Observations1.2M | Result date |
| Rank14 | ModelDE | Organizationdeepseek | Rating / score0.0 | VotesN/A | Observations3M | Result date |
| Rank16 | ModelME | Organizationmeta | Rating / score0.0 | VotesN/A | Observations2.3M | Result date |
| Rank18 | ModelAN | Organizationanthropic | Rating / score0.0 | VotesN/A | Observations1.7M | Result date |
| Rank20 | ModelAN | Organizationanthropic | Rating / score0.0 | VotesN/A | Observations1.3M | Result date |
| Rank21 | ModelXA | Organizationxai | Rating / score0.0 | VotesN/A | Observations1.1M | Result date |
| Rank24 | ModelAN | Organizationanthropic | Rating / score0.0 | VotesN/A | Observations1.2M | Result date |
| Rank26 | ModelAN | Organizationanthropic | Rating / score0.0 | VotesN/A | Observations2.3M | Result date |
| Rank27 | ModelMI | Organizationminimax | Rating / score0.0 | VotesN/A | Observations608.1K | Result date |
| Rank28 | ModelXA | Organizationxai | Rating / score0.0 | VotesN/A | Observations5.2M | Result date |
| Rank29 | ModelGO | Organizationgoogle | Rating / score0.0 | VotesN/A | Observations2.2M | Result date |
| Rank30 | ModelMI | Organizationminimax | Rating / score0.0 | VotesN/A | Observations1.9M | Result date |
| Rank31 | ModelAC | Organizationalibaba | Rating / score0.0 | VotesN/A | Observations1.2M | Result date |
| Rank32 | ModelTHInklingThinkingmachines | Organizationthinky | Rating / score0.0 | VotesN/A | Observations1.2M | Result date |
| Rank33 | ModelNV | Organizationnvidia | Rating / score0.0 | VotesN/A | Observations142.5K | Result date |
| Rank34 | ModelUP | Organizationupstage | Rating / score0.0 | VotesN/A | Observations151K | Result date |
| Rank35 | ModelGO | Organizationgoogle | Rating / score0.0 | VotesN/A | Observations460.9K | Result date |
| Rank36 | ModelDE | Organizationdeepseek | Rating / score0.0 | VotesN/A | Observations1.3M | Result date |
| Rank38 | ModelAC | Organizationalibaba | Rating / score0.0 | VotesN/A | Observations645.6K | Result date |
| Rank39 | ModelAC | Organizationalibaba | Rating / score0.0 | VotesN/A | Observations533.2K | Result date |
| Rank40 | ModelXI | Organizationxiaomi | Rating / score0.0 | VotesN/A | Observations1.2M | Result date |
| Rank41 | ModelGO | Organizationgoogle | Rating / score-0.0 | VotesN/A | Observations481.3K | Result date |
| Rank42 | ModelZA | Organizationzai | Rating / score-0.0 | VotesN/A | Observations3M | Result date |
| Rank43 | ModelGO | Organizationgoogle | Rating / score-0.0 | VotesN/A | Observations1.6M | Result date |
| Rank45 | ModelTE | Organizationtencent | Rating / score-0.0 | VotesN/A | Observations583.7K | Result date |
| Rank46 | ModelDE | Organizationdeepseek | Rating / score-0.0 | VotesN/A | Observations1.1M | Result date |
| Rank47 | ModelMA | Organizationmistral | Rating / score-0.0 | VotesN/A | Observations153.8K | Result date |
| Rank48 | ModelAN | Organizationanthropic | Rating / score-0.3 | VotesN/A | Observations1.3M | Result date |
| Rank49 | ModelGO | Organizationgoogle | Rating / score-0.3 | VotesN/A | Observations592.7K | Result date |
Agent Tool Hallucination Rating Distribution
A closer view of the leading model ratings.
The Top AI Models for Agent Tool Hallucination
The first five models in this source ranking, with price and output speed included when a canonical model match is available.
Ranking basisThis agent tool hallucination AI model leaderboard uses the source agent score and Arena rank. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01OPGPT-5.6 TerraOpenAI
- agent score
- 0.01
- Price
- $2.0 input / $12 output per 1M tokens
- Speed
- Up to 35 tok/s via OpenAI
Strengths
- Ranks #1 on Agent Tool Hallucination
- 693,841 observations support the result
- Matched official PAYG token pricing is available
Considerations
- Arena results are independent from the LLMBoard capability score
- 02MAKimi K3Moonshot AI
- agent score
- 0.01
- Price
- $3.0 input / $15 output per 1M tokens
- Speed
- Up to 26 tok/s via Fireworks
Strengths
- Ranks #2 on Agent Tool Hallucination
- 2,305,107 observations support the result
- Matched official PAYG token pricing is available
Considerations
- Arena results are independent from the LLMBoard capability score
- 03OPGPT-5.5OpenAI
- agent score
- 0.01
- Price
- $5.0 input / $30 output per 1M tokens
Strengths
- Ranks #3 on Agent Tool Hallucination
- 1,544,032 observations support the result
- Matched official PAYG token pricing is available
Considerations
- Arena results are independent from the LLMBoard capability score
- 04OPGPT-5.4OpenAI
- agent score
- 0.01
- Price
- $2.5 input / $15 output per 1M tokens
- Speed
- Up to 9.1 tok/s via OpenAI
Strengths
- Ranks #4 on Agent Tool Hallucination
- 2,855,616 observations support the result
- Matched official PAYG token pricing is available
Considerations
- Arena results are independent from the LLMBoard capability score
- 05XAGrok 4.5xAI
- agent score
- 0.01
- Price
- $2.0 input / $6.0 output per 1M tokens
- Speed
- Up to 4.3 tok/s via xAI
Strengths
- Ranks #5 on Agent Tool Hallucination
- 1,326,811 observations support the result
- Matched official PAYG token pricing is available
Considerations
- Arena results are independent from the LLMBoard capability score
Selection summary
Best AI Models for Agent Tool Hallucination
GPT-5.6 Terra currently leads Agent Tool Hallucination at 0.01. The best AI model for this use case may change when price, speed and independent benchmark capability are considered.
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.
What is the Agent Tool Hallucination Arena?
What Agent Tool Hallucination measures and how to read its results.
Agent Tool Hallucination reports agent score values and currently defines 1 evaluation category.
Arena results are preference or task-outcome signals. They are not automatically equivalent to capability benchmark scores.
FAQ
Common questions about Agent Tool Hallucination.
Which model leads Agent Tool Hallucination?
GPT-5.6 Terra is currently ranked first.
What does Agent Tool Hallucination measure?
This Arena reports agent score values across 1 configured evaluation category.
Does this result affect the LLMBoard score?
No. Arena results remain a separate preference or task-outcome signal.
How many models are included?
40 model results are currently shown.