reasoning benchmark
MT-Bench
MT-Bench is a challenging multi-turn benchmark that measures the ability of large language models to engage in coherent, informative, and engaging conversations. It uses strong LLMs as judges for scalable and explainable evaluation of multi-turn dialogue capabilities.
Updated Aug 11, 2026
Models12
Model coverage12
MetricNormalized score
EvidenceB
MT-Bench Ranking
Higher normalized score ranks better on this benchmark.
| 01 | AC | 93.5% | 100.0% | 12 | C | |
| 02 | NV | 91.7% | 90.9% | 12 | C | |
| 03 | DE | 90.2% | 81.8% | 12 | C | |
| 04 | NR | 89.9% | 72.7% | 12 | C | |
| 05 | AC | 87.5% | 63.6% | 12 | C | |
| 06 | MA | 86.3% | 54.5% | 12 | C | |
| 07 | AC | 84.1% | 45.5% | 12 | C | |
| 08 | MA | 83.5% | 36.4% | 12 | C | |
| 09 | MA | 83.0% | 27.3% | 12 | C | |
| 10 | NV | 81.0% | 18.2% | 12 | C | |
| 11 | MA | 76.8% | 9.1% | 12 | C | |
| 12 | NV | 9.0% | 0.0% | 12 | C |
MT-Bench Score Distribution
A closer view of the leading scores on this benchmark.
MT-Bench Highlights
The leading models and scores on this benchmark.
What is MT-Bench?
What MT-Bench measures and how its scores work.
MT-Bench is a challenging multi-turn benchmark that measures the ability of large language models to engage in coherent, informative, and engaging conversations. It uses strong LLMs as judges for scalable and explainable evaluation of multi-turn dialogue capabilities.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MT-Bench
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- mt-bench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MT-Bench.
Which model scores highest on MT-Bench?
Qwen2.5 72B Instruct is currently ranked first with 93.5%.
What does MT-Bench measure?
MT-Bench is a challenging multi-turn benchmark that measures the ability of large language models to engage in coherent, informative, and engaging conversations. It uses strong LLMs as judges for scalable and explainable evaluation of multi-turn dialogue capabilities.
Is a higher normalized score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
12 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.