Kimi Chinese in-house open-ended benchmark
Only in system cards
Models answer held-out Chinese prompts drawn from real user queries. Outputs are compared pairwise against another model to give win, tie and loss rates.
In-house Moonshot AI evaluation. Access to the data is restricted.
Made by Moonshot AI Released Jul 2025 Overall chat quality Tasks kept private Last in a system card Jul 2025
Last model added Jul 2025
- Level
- Everyday Most adults, without training
- Scored
- Ranked by matches Models play against each other, and the results become ratings.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
1
System card reports it, from 1 lab
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for Kimi Chinese in-house open-ended benchmark yet.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
One system card reports it
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 21 Jul 2025 | Kimi K2 technical report | Chinese in-house open-ended benchmark, win/tie/loss with no overall score: vs DeepSeek-V3-0324 59.6/23.5/16.9, vs Claude-Sonnet-4 64.6/18.8/16.6, vs ChatGPT-4o-latest 65.4/17.6/17.0 (Figure 11) | Capabilities |
More in Instructions and chat
- IFEval In use Models answer about 500 prompts containing verifiable instructions such as word limits or required keywords. Code checks each instruction for strict and loose accuracy.
Gemma 4 31B IT 98.9% - IFBench In use 58 new out-of-domain verifiable output constraints. Scored by programmatic constraint checks (strict or loose).
Nemotron-Cascade 2 30B-A3B 82.9% - MultiChallenge In use Multi-turn conversations testing instruction retention, inference memory, versioned editing and self-coherence. Graded by LLM judge with rubrics. GPT-6.1 Sol 82%
- Multi-IF In use Models follow verifiable instructions over three-turn conversations in eight languages, extending IFEval. Scored by instruction accuracy at each turn. LFM3-1.7B 89.1%
- AdvancedIF In use Models respond to over 1,600 prompts with complex, multi-turn, and system-level instructions. A judge model checks each response against expert-written rubrics.
MAI-Thinking-1 85% - IFStruct In use Models generate JSON or YAML that must follow a requested schema and phrasing constraints, without constrained decoding. A response passes only if every structural constraint holds. LFM3-1.7B 93.7%