MTVA-Bench - Conversation: leaderboard
Metric: Score (0-100). Source: arxiv.org. Saturation forecast: Around December 2026. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol | 74.1 |
| 2 | Gemini 3.6 Flash | 56.6 |
| 3 | GPT-5.6 Luna | 54.2 |
| 4 | GPT-5.2 | 44.9 |
| 5 | Qwen 3.8 27B | 36.3 |
Interactive version: theaggregate.ai/benchmark?slug=mtva-bench-conversation · How It Works · Data refreshed daily, snapshot 2026-09-24.