TIGER-Lab (University of Waterloo)
We track 5 benchmarks and 4 arenas that TIGER-Lab (University of Waterloo) made or helped make. Its models are on its lab page.
1 in use 8 with public code 5 with a leaderboard here
Benchmarks
| Name | Kind | Released | Best score | Status |
|---|---|---|---|---|
| MMLU-Pro Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects. | Exam questions | Jun 2024 | | In use |
| VideoEval-Pro Video models give open-ended short answers to questions that need the whole long video, which removes the guessing that multiple choice allows. | Long videos | May 2025 | 40.8% | Fading |
| MEGA-Bench Models solve 505 real-world multimodal tasks with over 8,000 samples. Outputs include numbers, code, LaTeX, coordinates and JSON, scored by more than 40 task metrics. | General visual questions | Oct 2024 | 54.3% | System cards only |
| VideoScore-Bench Models rate generated videos or choose which video better matches a human preference. The four test sets compare model judgments with human judgments. | Video understanding | Jun 2024 | | Not in cards |
| VideoScore-Bench v2 Models score 500 generated videos on visual quality, agreement with the prompt, and physical consistency. The evaluation checks their ratings against human scores. | Video understanding | Sep 2025 | 28.9% | Not in cards |
Arenas
| Name | Kind | Released | Best score | Status |
|---|---|---|---|---|
| GenAI-Arena Users compare outputs from two anonymous models for image generation, image editing and video generation, and vote. Votes give Elo ratings. | Image generation and editing | Jun 2024 | 1,133 | Not in cards |
| GenAI-Arena Image Generation Models generate images from text prompts. Anonymous human comparisons determine Elo in this independent vote pool. | Image generation and editing | Jun 2024 | 1,133 | Not in cards |
| GenAI-Arena Image Editing Models edit images from user instructions. Anonymous human comparisons determine Elo in this independent vote pool. | Image generation and editing | Jun 2024 | Not in cards | |
| GenAI-Arena Video Generation Models generate videos from text prompts. Anonymous human comparisons determine Elo in this independent vote pool. | Image generation and editing | Jun 2024 | Not in cards |