MM-MT-Bench
A multi-turn LLM-as-a-judge evaluation benchmark for testing multimodal instruction-tuned models' ability to follow user instructions in multi-turn dialogues and answer open-ended questions in a zero-shot manner.
Mistral Large 3 from Mistral AI currently leads the MM-MT-Bench leaderboard with a score of 84.900 across 17 evaluated AI models.
Mistral Large 3 leads with 84.9%, followed by 
Qwen3 VL 235B A22B Instruct at 8.5% and Qwen3 VL 235B A22B Thinking at 8.5%.
Progress Over Time
Interactive timeline showing model performance evolution on MM-MT-Bench
MM-MT-Bench Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | Mistral AI | 675B | — | — | ||
| 2 |  Alibaba Cloud / Qwen Team | 236B | 262K | $0.30 / $1.49 | ||
| 2 | Alibaba Cloud / Qwen Team | 236B | 262K | $0.45 / $3.49 | ||
| 4 | Alibaba Cloud / Qwen Team | 33B | — | — | ||
| 5 | Alibaba Cloud / Qwen Team | 33B | — | — | ||
| 6 | Alibaba Cloud / Qwen Team | 31B | — | — | ||
| 7 | Alibaba Cloud / Qwen Team | 9B | 262K | $0.18 / $2.09 | ||
| 8 | Alibaba Cloud / Qwen Team | 31B | — | — | ||
| 9 | Alibaba Cloud / Qwen Team | 9B | 262K | $0.08 / $0.50 | ||
| 9 | Alibaba Cloud / Qwen Team | 4B | 262K | $0.10 / $1.00 | ||
| 11 | Alibaba Cloud / Qwen Team | 4B | 262K | $0.10 / $0.60 | ||
| 12 | Mistral AI | 124B | — | — | ||
| 13 | Mistral AI | 12B | — | — | ||
| 14 | Mistral AI | 14B | — | — | ||
| 15 | Mistral AI | 8B | — | — | ||
| 16 | Mistral AI | 3B | — | — | ||
| 17 | Alibaba Cloud / Qwen Team | 7B | — | — |
FAQ
Common questions about MM-MT-Bench.
More evaluations to explore
Related benchmarks in the same category
MMMU (Massive Multi-discipline Multimodal Understanding) is a benchmark designed to evaluate multimodal models on college-level subject knowledge and deliberate reasoning. Contains 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering across 30 subjects and 183 subfields.
A more robust multi-discipline multimodal understanding benchmark that enhances MMMU through a three-step process: filtering text-only answerable questions, augmenting candidate options, and introducing vision-only input settings. Achieves significantly lower model performance (16.8-26.9%) compared to original MMMU, providing more rigorous evaluation that closely mimics real-world scenarios.
CharXiv-R is the reasoning component of the CharXiv benchmark, focusing on complex reasoning questions that require synthesizing information across visual chart elements. It evaluates multimodal large language models on their ability to understand and reason about scientific charts from arXiv papers through various reasoning tasks.
MathVista evaluates mathematical reasoning of foundation models in visual contexts. It consists of 6,141 examples derived from 28 existing multimodal datasets and 3 newly created datasets (IQTest, FunctionQA, and PaperQA), combining challenges from diverse mathematical and visual tasks to assess models' ability to understand complex figures and perform rigorous reasoning.
AI2D is a dataset of 4,903 illustrative diagrams from grade school natural sciences (such as food webs, human physiology, and life cycles) with over 15,000 multiple choice questions and answers. The benchmark evaluates diagram understanding and visual reasoning capabilities, requiring models to interpret diagrammatic elements, relationships, and structure to answer questions about scientific concepts represented in visual form.
τ²-Bench telecom domain evaluates conversational agents in a dual-control environment modeled as a Dec-POMDP, where both agent and user use tools in shared telecommunications troubleshooting scenarios that test coordination and communication capabilities.