reasoning benchmark
Wild Bench Leaderboard
Wild Bench is an automated evaluation framework for large language models using 1,024 challenging, real-world tasks selected from over one million human-chatbot conversation logs.
Updated Sep 5, 2026
Models8
Model coverage8
MetricScore
EvidenceB
Wild Bench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMA | Score68.50% | Percentile100.00% | Participants8 | EvidenceC | Evaluated |
| Rank02 | ModelMA | Score68.50% | Percentile85.71% | Participants8 | EvidenceC | Evaluated |
| Rank03 | ModelMA | Score66.80% | Percentile71.43% | Participants8 | EvidenceC | Evaluated |
| Rank04 | ModelMA | Score65.33% | Percentile57.14% | Participants8 | EvidenceC | Evaluated |
| Rank05 | ModelMA | Score56.80% | Percentile42.86% | Participants8 | EvidenceC | Evaluated |
| Rank06 | ModelMA | Score52.20% | Percentile28.57% | Participants8 | EvidenceC | Evaluated |
| Rank07 | ModelAL | Score48.50% | Percentile14.29% | Participants8 | EvidenceC | Evaluated |
| Rank08 | ModelAL | Score42.40% | Percentile0.00% | Participants8 | EvidenceC | Evaluated |
Wild Bench Highlights
The leading models and scores on this benchmark.
Wild Bench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Wild Bench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is Wild Bench?
What Wild Bench measures and how its scores work.
WildBench is an automated evaluation framework that benchmarks large language models on 1,024 challenging, real-world tasks.
It measures model performance using WB-Reward and WB-Score with task-specific checklists.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Wild Bench
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Wild Bench.
Which model scores highest on Wild Bench?
MiniStral 3 (14B Instruct 2512) is currently ranked first with 68.50%.
What are the top three models on Wild Bench?
The current leaders are MiniStral 3 (14B Instruct 2512) (68.50%), Mistral Large 3 (68.50%), and Ministral 3 (8B Instruct 2512) (66.80%).
Which Wild Bench model has the lowest official input price?
MiniStral 3 (14B Instruct 2512) has the lowest matched official input price at $0.10 input / $0.10 output per 1M tokens.
Which models are fastest among Wild Bench results?
The fastest matched records are Mistral Small 3 24B Instruct (134.00 tok/s via Mistral AI), Jamba 1.5 Mini (100.00 tok/s via Google), and Jamba 1.5 Large (42.00 tok/s via Google).
Does the highest 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.