BlogLLM Benchmark Scores as Published, Side by Side
CL-bench: Results as Published
Every result the catalog holds for CL-bench: 5 models from 4 developers, read from 1 page. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area General Knowledge and ReasoningMaintainer CL-bench authorsIntroduced 2026Data version 2026103001, as of 2026-10-30
CL-bench tests learning from context: a task supplies new rules, knowledge or procedures in the prompt and the model has to apply them to questions that cannot be answered from training data. Answers are scored against released rubrics.
Not checked against a maintainer's page.
CL-bench
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5.5OpenAI, released 2026-04-23 | 25.38% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| Claude Opus 4.7Anthropic, released 2026-04-16 | 22.92% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| Gemini 3.1 Pro PreviewGoogle, released 2026-02-19 | 21.06% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| MiniMax M3MiniMax, released 2026-06-01 | 20.48% | MiniMax, MiniMax M3checked 2026-10-15 | - |
| MiniMax M2.7MiniMax, released 2026-03-18 | 15.38% | MiniMax, MiniMax M3checked 2026-10-15 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.