BlogLLM Benchmark Scores as Published, Side by Side
Longform Writing: Results as Published
Every result the catalog holds for Longform Writing: 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 Writing and ConversationMaintainer Moonshot AIIntroduced 2025Data version 2026103001, as of 2026-10-30
Longform Writing is the long-form writing evaluation Moonshot AI prints on its Kimi K2 release pages: the model writes extended pieces to a brief and the output is scored for quality, printed as a 0-100 score. The pages do not publish the prompts, the rubric or the judge.
Not checked against a maintainer's page.
Longform Writing
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5OpenAI, released 2025-08-07 | 71.4 | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Effort: high; Tools: none |
| Claude Sonnet 4.5Anthropic, released 2025-09-29 | 79.8 | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Effort: thinking; Tools: none |
| DeepSeek-V3.2-ExpDeepSeek, released 2025-09-29 | 72.5 | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: none |
| Kimi K2 ThinkingMoonshot AI, released 2025-11-06 | 73.8 | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Effort: thinking; Tools: none |
| Kimi K2 Instruct 0905Moonshot AI, released 2025-09-05 | 62.8 | Moonshot AI, Kimi K2 Thinking release pagechecked 2026-10-15 | Tools: none |
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.