Unspecified benchmark
LM Arena Agent Bash Reliability No Prereq Leaderboard
LM Arena Agent Bash Reliability No Prereq is listed with a current leaderboard and an Agent Score measured as a ratio.
Updated Oct 23, 2026
Models45
Model coverage45
MetricAgent Score
EvidenceA
LM Arena Agent Bash Reliability No Prereq Ranking
Higher agent score ranks better on this benchmark.
Sort by
Rank | Model | Agent Score | Percentile | Participants | Observations | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Agent Score15.74% (13.50% - 17.98%) | Percentile100.00% | Participants45 | Observations12.2K | EvidenceA | Evaluated |
| Rank02 | ModelAN | Agent Score15.57% (14.52% - 16.62%) | Percentile97.73% | Participants45 | Observations44.5K | EvidenceA | Evaluated |
| Rank03 | ModelOP | Agent Score13.33% (11.83% - 14.83%) | Percentile95.45% | Participants45 | Observations20.1K | EvidenceA | Evaluated |
| Rank04 | ModelAN | Agent Score12.87% (11.21% - 14.52%) | Percentile93.18% | Participants45 | Observations33.5K | EvidenceA | Evaluated |
| Rank05 | ModelOP | Agent Score11.91% (10.67% - 13.14%) | Percentile90.91% | Participants45 | Observations45.3K | EvidenceA | Evaluated |
| Rank06 | ModelAN | Agent Score11.85% (10.79% - 12.91%) | Percentile88.64% | Participants45 | Observations55.9K | EvidenceA | Evaluated |
| Rank07 | ModelGO | Agent Score11.23% (10.72% - 11.75%) | Percentile86.36% | Participants45 | Observations408.8K | EvidenceA | Evaluated |
| Rank08 | ModelAN | Agent Score10.80% (9.70% - 11.91%) | Percentile84.09% | Participants45 | Observations49.2K | EvidenceA | Evaluated |
| Rank09 | ModelOP | Agent Score10.71% (8.72% - 12.69%) | Percentile81.82% | Participants45 | Observations10.7K | EvidenceA | Evaluated |
| Rank10 | ModelOP | Agent Score10.25% (8.36% - 12.14%) | Percentile79.55% | Participants45 | Observations19.3K | EvidenceA | Evaluated |
| Rank11 | ModelXA | Agent Score9.24% (8.02% - 10.45%) | Percentile77.27% | Participants45 | Observations38.5K | EvidenceA | Evaluated |
| Rank12 | ModelXA | Agent Score8.98% (8.16% - 9.79%) | Percentile75.00% | Participants45 | Observations142.3K | EvidenceA | Evaluated |
| Rank13 | ModelAN | Agent Score7.78% (6.85% - 8.71%) | Percentile72.73% | Participants45 | Observations80K | EvidenceA | Evaluated |
| Rank14 | ModelGO | Agent Score7.63% (6.31% - 8.95%) | Percentile70.45% | Participants45 | Observations97.3K | EvidenceA | Evaluated |
| Rank15 | ModelOP | Agent Score7.39% (6.44% - 8.34%) | Percentile68.18% | Participants45 | Observations130.1K | EvidenceA | Evaluated |
| Rank16 | ModelAC | Agent Score6.43% (3.71% - 9.15%) | Percentile65.91% | Participants45 | Observations22.6K | EvidenceA | Evaluated |
| Rank17 | ModelTM | Agent Score4.97% (0.80% - 9.15%) | Percentile63.64% | Participants45 | Observations7.4K | EvidenceA | Evaluated |
| Rank18 | ModelXI | Agent Score4.23% (3.17% - 5.30%) | Percentile61.36% | Participants45 | Observations148.5K | EvidenceA | Evaluated |
| Rank19 | ModelGO | Agent Score3.31% (-1.04% - 7.66%) | Percentile59.09% | Participants45 | Observations14.8K | EvidenceA | Evaluated |
| Rank20 | ModelTM | Agent Score2.71% (-2.09% - 7.52%) | Percentile56.82% | Participants45 | Observations7K | EvidenceA | Evaluated |
| Rank21 | ModelME | Agent Score2.42% (1.50% - 3.34%) | Percentile54.55% | Participants45 | Observations328.8K | EvidenceA | Evaluated |
| Rank22 | ModelDE | Agent Score2.36% (1.06% - 3.66%) | Percentile52.27% | Participants45 | Observations79.6K | EvidenceA | Evaluated |
| Rank23 | ModelOP | Agent Score2.32% (-0.17% - 4.81%) | Percentile50.00% | Participants45 | Observations26.7K | EvidenceA | Evaluated |
| Rank24 | ModelMI | Agent Score2.29% (0.14% - 4.44%) | Percentile47.73% | Participants45 | Observations33.1K | EvidenceA | Evaluated |
| Rank25 | ModelMA | Agent Score2.14% (-0.12% - 4.40%) | Percentile45.45% | Participants45 | Observations43K | EvidenceA | Evaluated |
| Rank26 | ModelAC | Agent Score1.43% (0.66% - 2.21%) | Percentile43.18% | Participants45 | Observations244.1K | EvidenceA | Evaluated |
| Rank27 | ModelXI | Agent Score0.96% (-1.22% - 3.14%) | Percentile40.91% | Participants45 | Observations33K | EvidenceA | Evaluated |
| Rank28 | ModelGO | Agent Score0.52% (-2.26% - 3.29%) | Percentile38.64% | Participants45 | Observations22K | EvidenceA | Evaluated |
| Rank29 | ModelAC | Agent Score-0.64% (-6.02% - 4.74%) | Percentile36.36% | Participants45 | Observations12.1K | EvidenceA | Evaluated |
| Rank30 | ModelXA | Agent Score-1.21% (-3.46% - 1.04%) | Percentile34.09% | Participants45 | Observations20.7K | EvidenceA | Evaluated |
LM Arena Agent Bash Reliability No Prereq Highlights
The leading models and scores on this benchmark.
LM Arena Agent Bash Reliability No Prereq Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for LM Arena Agent Bash Reliability No Prereq
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 Bash Reliability No Prereq?
What LM Arena Agent Bash Reliability No Prereq measures and how its scores work.
LM Arena Agent Bash Reliability No Prereq is a benchmark with a current leaderboard.
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-bash-reliability-no-prereq
- 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 Bash Reliability No Prereq.
Which model scores highest on LM Arena Agent Bash Reliability No Prereq?
Claude Opus 4.8 is currently ranked first with 15.74%.
What are the top three models on LM Arena Agent Bash Reliability No Prereq?
The current leaders are Claude Opus 4.8 (15.74%), Claude Sonnet 5 (15.57%), and GPT-5.5 (13.33%).
Which LM Arena Agent Bash Reliability No Prereq model has the lowest official input price?
Claude Haiku 5.5 has the lowest matched official input price at $0.10 input / $0.50 output per 1M tokens.
Which models are fastest among LM Arena Agent Bash Reliability No Prereq results?
The fastest matched records are Gemini 3.7 Flash (409.96 tok/s via Google), GPT-5.6 Luna (215.52 tok/s via OpenAI), and Gemini 3.1 Pro (90.00 tok/s via Google).