Unspecified benchmark
LM Arena Agent Praise Complaint Leaderboard
LM Arena Agent Praise Complaint is a current leaderboard using the Agent Score metric, reported as a ratio.
Updated Sep 8, 2026
Models49
Model coverage49
MetricAgent Score
EvidenceA
LM Arena Agent Praise Complaint Ranking
Higher agent score ranks better on this benchmark.
Sort by
Rank | Model | Agent Score | Percentile | Participants | Observations | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Agent Score42.45% (31.51% - 53.39%) | Percentile100.00% | Participants49 | Observations680 | EvidenceA | Evaluated |
| Rank02 | ModelOP | Agent Score22.07% (16.58% - 27.57%) | Percentile97.92% | Participants49 | Observations7.8K | EvidenceA | Evaluated |
| Rank03 | ModelAN | Agent Score19.36% (14.07% - 24.65%) | Percentile95.83% | Participants49 | Observations9K | EvidenceA | Evaluated |
| Rank04 | ModelAN | Agent Score18.27% (11.78% - 24.76%) | Percentile93.75% | Participants49 | Observations6.7K | EvidenceA | Evaluated |
| Rank05 | ModelAN | Agent Score18.04% (12.85% - 23.23%) | Percentile91.67% | Participants49 | Observations8.4K | EvidenceA | Evaluated |
| Rank06 | ModelGO | Agent Score14.25% (8.00% - 20.51%) | Percentile89.58% | Participants49 | Observations1.6K | EvidenceA | Evaluated |
| Rank07 | ModelMA | Agent Score14.03% (11.67% - 16.39%) | Percentile87.50% | Participants49 | Observations28.8K | EvidenceA | Evaluated |
| Rank08 | ModelZA | Agent Score11.73% (9.06% - 14.41%) | Percentile85.42% | Participants49 | Observations15.4K | EvidenceA | Evaluated |
| Rank09 | ModelOP | Agent Score11.41% (7.63% - 15.18%) | Percentile83.33% | Participants49 | Observations12.8K | EvidenceA | Evaluated |
| Rank10 | ModelAN | Agent Score11.19% (4.41% - 17.98%) | Percentile81.25% | Participants49 | Observations5.9K | EvidenceA | Evaluated |
| Rank11 | ModelTE | Agent Score10.26% (4.65% - 15.87%) | Percentile79.17% | Participants49 | Observations2.3K | EvidenceA | Evaluated |
| Rank12 | ModelAN | Agent Score10.01% (5.13% - 14.89%) | Percentile77.08% | Participants49 | Observations8.2K | EvidenceA | Evaluated |
| Rank13 | ModelAN | Agent Score6.76% (2.03% - 11.50%) | Percentile75.00% | Participants49 | Observations9.5K | EvidenceA | Evaluated |
| Rank14 | ModelAC | Agent Score6.58% (2.78% - 10.39%) | Percentile72.92% | Participants49 | Observations5.4K | EvidenceA | Evaluated |
| Rank15 | ModelZA | Agent Score5.75% (3.35% - 8.16%) | Percentile70.83% | Participants49 | Observations14K | EvidenceA | Evaluated |
| Rank16 | ModelZA | Agent Score5.45% (1.97% - 8.94%) | Percentile68.75% | Participants49 | Observations5.4K | EvidenceA | Evaluated |
| Rank17 | ModelDE | Agent Score5.24% (2.11% - 8.37%) | Percentile66.67% | Participants49 | Observations7.2K | EvidenceA | Evaluated |
| Rank18 | ModelXA | Agent Score5.07% (1.04% - 9.09%) | Percentile64.58% | Participants49 | Observations7.9K | EvidenceA | Evaluated |
| Rank19 | ModelMA | Agent Score5.02% (-4.26% - 14.30%) | Percentile62.50% | Participants49 | Observations1.8K | EvidenceA | Evaluated |
| Rank20 | ModelDE | Agent Score3.90% (1.14% - 6.67%) | Percentile60.42% | Participants49 | Observations13.7K | EvidenceA | Evaluated |
| Rank21 | ModelXA | Agent Score3.77% (-0.34% - 7.87%) | Percentile58.33% | Participants49 | Observations5.3K | EvidenceA | Evaluated |
| Rank22 | ModelOP | Agent Score1.41% (-2.61% - 5.42%) | Percentile56.25% | Participants49 | Observations5.2K | EvidenceA | Evaluated |
| Rank23 | ModelGO | Agent Score1.11% (-1.68% - 3.90%) | Percentile54.17% | Participants49 | Observations25.1K | EvidenceA | Evaluated |
| Rank24 | ModelMA | Agent Score0.99% (-8.04% - 10.02%) | Percentile52.08% | Participants49 | Observations1.7K | EvidenceA | Evaluated |
| Rank25 | ModelAC | Agent Score0.78% (-2.50% - 4.06%) | Percentile50.00% | Participants49 | Observations5.6K | EvidenceA | Evaluated |
| Rank26 | ModelOP | Agent Score0.71% (-2.35% - 3.76%) | Percentile47.92% | Participants49 | Observations16.7K | EvidenceA | Evaluated |
| Rank27 | ModelAC | Agent Score0.24% (-3.91% - 4.39%) | Percentile45.83% | Participants49 | Observations3.4K | EvidenceA | Evaluated |
| Rank28 | ModelOP | Agent Score-0.22% (-3.85% - 3.40%) | Percentile43.75% | Participants49 | Observations5.4K | EvidenceA | Evaluated |
| Rank29 | ModelAN | Agent Score-0.50% (-4.49% - 3.49%) | Percentile41.67% | Participants49 | Observations10.7K | EvidenceA | Evaluated |
| Rank30 | ModelGO | Agent Score-1.38% (-4.01% - 1.26%) | Percentile39.58% | Participants49 | Observations26.3K | EvidenceA | Evaluated |
LM Arena Agent Praise Complaint Highlights
The leading models and scores on this benchmark.
LM Arena Agent Praise Complaint Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for LM Arena Agent Praise Complaint
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is LM Arena Agent Praise Complaint?
What LM Arena Agent Praise Complaint measures and how its scores work.
A current leaderboard for LM Arena Agent Praise Complaint.
It reports Agent Score as a ratio.
Scores are shown in ratio. This benchmark is verified and has an evidence level of A.
- Family
- lm-arena-agent-praise-complaint
- Modality
- Unspecified
- Primary category
- Unspecified
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LM Arena. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about LM Arena Agent Praise Complaint.
Which model scores highest on LM Arena Agent Praise Complaint?
Claude Fable 5.1 is currently ranked first with 42.45%.
What are the top three models on LM Arena Agent Praise Complaint?
The current leaders are Claude Fable 5.1 (42.45%), GPT-5.6 Sol (22.07%), and Claude Fable 5 (19.36%).
Which LM Arena Agent Praise Complaint model has the lowest official input price?
GLM-5.3-Flash has the lowest matched official input price at $0.08 input / $0.25 output per 1M tokens.
Which models are fastest among LM Arena Agent Praise Complaint results?
The fastest matched records are GLM-5.3 (472.69 tok/s via FriendliAI), Gemini 3.5 Flash (210.94 tok/s via Google), and GPT-5.5 (134.94 tok/s via OpenAI).
Does the highest agent score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.