multimodal benchmark
MM-MT-Bench Leaderboard
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.
Updated Aug 17, 2026
Models17
Model coverage17
MetricScore
EvidenceB
MM-MT-Bench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMA | Score84.9 points | Percentile100.0% | Participants17 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score8.3 points | Percentile93.8% | Participants17 | EvidenceC | Evaluated |
| Rank03 | ModelMA | Score0.74 points | Percentile87.5% | Participants17 | EvidenceC | Evaluated |
| Rank04 | ModelMA | Score0.605 points | Percentile81.3% | Participants17 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score8.5 points | Percentile75.0% | Participants17 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score8.5 points | Percentile68.8% | Participants17 | EvidenceC | Evaluated |
| Rank07 | ModelMA | Score0.085 points | Percentile62.5% | Participants17 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score8.4 points | Percentile56.3% | Participants17 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score8.1 points | Percentile50.0% | Participants17 | EvidenceC | Evaluated |
| Rank10 | ModelMA | Score0.081 points | Percentile43.8% | Participants17 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score8 points | Percentile37.5% | Participants17 | EvidenceC | Evaluated |
| Rank12 | ModelAC | Score7.9 points | Percentile31.3% | Participants17 | EvidenceC | Evaluated |
| Rank13 | ModelMA | Score0.078 points | Percentile25.0% | Participants17 | EvidenceC | Evaluated |
| Rank14 | ModelAC | Score7.7 points | Percentile18.8% | Participants17 | EvidenceC | Evaluated |
| Rank15 | ModelAC | Score7.7 points | Percentile12.5% | Participants17 | EvidenceC | Evaluated |
| Rank16 | ModelAC | Score7.5 points | Percentile6.3% | Participants17 | EvidenceC | Evaluated |
| Rank17 | ModelAC | Score0.06 points | Percentile0.0% | Participants17 | EvidenceC | Evaluated |
MM-MT-Bench Highlights
The leading models and scores on this benchmark.
MM-MT-Bench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MM-MT-Bench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis mm-mt-bench AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01MAMistral Large 3Mistral AI
- Score
- 84.9 points
- Price
- $0.50 input / $1.5 output per 1M tokens
- Speed
- Up to 0.78 tok/s via Mistral AI
Strengths
- Ranks #1 of 17 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures MM-MT-Bench, not total model capability
- 02ACQwen3 VL 32B ThinkingAlibaba Cloud / Qwen Team
- Score
- 8.3 points
Strengths
- Ranks #2 of 17 compared models
- 94th percentile on this benchmark
- C evidence result
Considerations
- This result measures MM-MT-Bench, not total model capability
- 03MAPixtral LargeMistral AI
- Score
- 0.74 points
- Speed
- Up to 0.10 tok/s via Mistral AI
Strengths
- Ranks #3 of 17 compared models
- 88th percentile on this benchmark
- C evidence result
Considerations
- This result measures MM-MT-Bench, not total model capability
- 04MAPixtral-12BMistral AI
- Score
- 0.605 points
- Price
- $0.15 input / $0.15 output per 1M tokens
- Speed
- Up to 0.10 tok/s via Mistral AI
Strengths
- Ranks #4 of 17 compared models
- 81th percentile on this benchmark
- C evidence result
Considerations
- This result measures MM-MT-Bench, not total model capability
- 05ACQwen3 VL 235B A22B InstructAlibaba Cloud / Qwen Team
- Score
- 8.5 points
Strengths
- Ranks #5 of 17 compared models
- 75th percentile on this benchmark
- C evidence result
Considerations
- This result measures MM-MT-Bench, not total model capability
Selection summary
Best AI Models for MM-MT-Bench
Mistral Large 3 currently leads MM-MT-Bench with 84.9 points. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is MM-MT-Bench?
What MM-MT-Bench measures and how its scores work.
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.
Scores are shown in points. This benchmark is not independently verified and has an evidence level of B.
- Family
- MM-MT-Bench
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- mm-mt-bench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MM-MT-Bench.
Which model scores highest on MM-MT-Bench?
Mistral Large 3 is currently ranked first with 84.9 points.
What does MM-MT-Bench measure?
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.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
17 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.