FireWorldBench - Temporal Evolution Forecasting (Rendered Images): leaderboard
Metric: Completion accuracy (%; P1, temporal evolution forecasting items of the controlled-simulation subset; image-observation track (physics-rendered field visualizations and 3D scene renderings); each cell is the mean of the matched choice-format score (Jaccard overlap of selected and gold option sets) and open-report score (exact agreement of required structured slots); deterministic evaluator, no LLM judge; failed or unparseable responses score 0). Source: arxiv.org. Saturation forecast: Around December 2026. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Luna | 60.74 |
| 2 | Qwen 3 VL 32B Instruct | 58.28 |
| 3 | Claude Haiku 4.5 | 56.04 |
| 4 | Gemini 2.5 Flash | 52.84 |
| 5 | InternVL3-78B | 45.96 |
| 6 | Qwen 3.5 Plus (2026-02-15) | 44.92 |
| 7 | InternVL3-38B | 41.94 |
| 8 | Qwen 3 VL 235B A22B Instruct | 38.02 |
| 9 | Qwen 3 VL 8B Instruct | 31.92 |
| 10 | InternVL3-8B | 26.86 |
Interactive version: theaggregate.ai/benchmark?slug=fireworldbench-temporal-evolution-forecasting-rendered-images · How It Works · Data refreshed daily, snapshot 2026-09-26.