multimodal benchmark
TIR-Bench
A tool-calling and multimodal interaction benchmark for testing visual instruction following and execution reliability.
Updated Aug 11, 2026
Models4
Model coverage4
MetricScore
EvidenceB
TIR-Bench Ranking
Higher score ranks better on this benchmark.
| 01 | AC | 61.6% | 100.0% | 4 | C | |
| 02 | AC | 59.8% | 66.7% | 4 | C | |
| 03 | AC | 55.5% | 33.3% | 4 | C | |
| 04 | AC | 53.2% | 0.0% | 4 | C |
TIR-Bench Score Distribution
A closer view of the leading scores on this benchmark.
TIR-Bench Highlights
The leading models and scores on this benchmark.
What is TIR-Bench?
What TIR-Bench measures and how its scores work.
A tool-calling and multimodal interaction benchmark for testing visual instruction following and execution reliability.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- TIR-Bench
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- tir-bench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about TIR-Bench.
Which model scores highest on TIR-Bench?
Qwen3.6 Plus is currently ranked first with 61.6%.
What does TIR-Bench measure?
A tool-calling and multimodal interaction benchmark for testing visual instruction following and execution reliability.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
4 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.