TIR-Bench — leaderboard

A tool-calling and multimodal interaction benchmark for testing visual instruction following and execution reliability.

Metric: Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 23 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro28.9
2O326.9
3Gemini 2.5 Flash25.2
4Grok 422.5
5InternVL3-78B21.4
6O4 Mini21.2
7InternVL3-38B19.1
8GPT-4.118.8
9GPT-4o17.3
10InternVL3-8B16.9

Interactive version: theaggregate.ai/benchmark?slug=tir-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.