docling-project: docling-models
1 benchmarks
Leaderboard position
#382
Overall rank (of 1122 models)
1350
Elo rating
1
Benchmarks
Top 34.0%
Percentile
In docling-project (of 1 models)
Above: Z.ai: glm-4.7-flash #381
Below: OpenAI: o3-mini #383
Benchmark highlights
Best benchmark
ParseBench
50.6
Worst benchmark
ParseBench
50.6
Nearest competitor from another company
The model from another company with the most similar benchmark scores.
appeared as nearest in 1 of 1 benchmarks
1/1
100.0%
Benchmarks
Predicted scores
Estimated from 25 similar models and the global Elo rating. These are projections, not measured results.
| Benchmark | Predicted | Confidence | Based on |
|---|---|---|---|
| Artificial Analysis Intelligence Index v5.0.1 | ~12 | 50% | — |
| MATH-500 | ~95.01 | 50% | — |
| AIME 2025 | ~82.48 | 50% | — |
| AIME 2026 | ~83.13 | 50% | — |
| HMMT Feb 2026 | ~74.69 | 50% | — |
| GPQA Diamond | ~69.04 | 50% | — |
| MMLU-Pro | ~73.45 | 50% | — |
| Humanity's Last Exam (no tools) | ~20.47 | 50% | — |
| IFEval | ~89.07 | 50% | — |
| IFBench | ~61.58 | 50% | — |
| HumanEval | ~88.13 | 50% | — |
| MBPP | ~93.7 | 50% | — |
| Terminal-Bench v2.1 | ~38.58 | 50% | — |
| MMLU | ~80.49 | 50% | — |
| SWE-bench Verified | ~54.77 | 50% | — |
| SWE-bench Pro | ~32.68 | 50% | — |
| SciCode | ~34.64 | 50% | — |
| AA-LCR | ~52.79 | 50% | — |
| Humanity's Last Exam (with tools) | ~27.59 | 50% | — |
| GSM8K | ~99.6 | 50% | — |
| -(CoderPPL) | ~-1.69 | 50% | — |
| LiveCodeBench v6 | ~67.3 | 50% | — |
| MMMU-Pro | ~62.27 | 50% | — |
| MATH | ~81.64 | 50% | — |
| BBH | ~76.38 | 50% | — |