CombEval: leaderboard
We present CombEval, a dynamic benchmark for evaluating combinatorial counting in large language models. CombEval represents each problem as a typed Cofola specification over entities, combinatorial objects, object dependencies, and constraints, enabling controlled generation of natural-language counting problems with exact solver-verified answers. Unlike static collections, CombEval supports syst
Metric: Avg. (self-reported). Source: benchmarklist.com. Saturation forecast: Around July 2027. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 93.6 | #31 |
| 2 | Gemini 3 Flash (Preview) (Thinking) | 86.5 | #82 (Gemini 3 Flash (Preview)) |
| 3 | GPT-5.1 | 74.1 | #135 |
| 4 | DeepSeek V3.2 | 71.4 | #205 |
| 5 | GPT-OSS-20B | 59.4 | #518 |
| 6 | Llama 3.3 70B Instruct | 36.6 | #534 |
| 7 | Qwen2.5-Math-7B-Instruct | 26.3 | #1444 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=combeval · How It Works · Data refreshed daily, snapshot 2026-10-20.