FireWorldBench - Real-World-Aligned (Structured Records): leaderboard
The real-world-aligned subset of FireWorldBench (Chen et al., 2026): 26 recorded indoor fire experiments reconstructed with the Fire Dynamics Simulator, with questions across the five physical-capability dimensions. Observations are given as structured sensor traces and physical records; the score is completion accuracy in percent averaged over the five dimensions and over matched multiple-choice and open-report questions and scored deterministically; higher is better.
Metric: Completion accuracy (%; equal-weight mean of P1-P5 on the 714-item real-world-aligned subset, 26 event groups reconstructed from recorded indoor fire experiments; structured-observation track (textual sensor traces and physical records); 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 July 2027. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Luna | 60.16 | #117 |
| 2 | Qwen 3.5 Plus (2026-02-15) | 55.35 | #178 |
| 3 | Claude Haiku 4.5 | 55.05 | #568 |
| 4 | Gemini 2.5 Flash | 54.35 | #452 |
| 5 | Llama 3.3 70B Instruct | 51.2 | #1353 |
| 6 | GLM 4.5 Air | 50.55 | #863 |
| 7 | Kimi K2 | 49.54 | #435 |
| 8 | DeepSeek V3.2 | 49.24 | #403 |
| 9 | Qwen 3 Next 80B A3B Instruct | 48.98 | #763 |
| 10 | Qwen 3 32B | 47.64 | #960 |
| 11 | Gemma 3 27B (IT) | 44.83 | #1306 |
| 12 | Qwen 3 235B A22B | 44.47 | #622 |
| 13 | Gemma 3 12B (IT) | 41.25 | #1849 |
| 14 | Qwen 3 8B | 39.09 | #1838 |
| 15 | Llama 3.1 8B Instruct | 32.54 | #4277 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=fireworldbench-real-world-aligned-structured-records · How It Works · Data refreshed daily, snapshot 2026-11-12.