BlogLLM Benchmark Scores as Published, Side by Side
AutoLogi: Results as Published
Every result the catalog holds for AutoLogi: 7 models from 6 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 Qin Zhu and co-authors (Fudan University and the Qwen team, Alibaba Group)Introduced 2025Data version 2026103001, as of 2026-10-30
AutoLogi tests open-ended logical reasoning in English and Chinese, instead of multiple choice. Puzzles are synthesized from background text and logical constraints, and a program checks both the answer format and the constraints. The benchmark split has 206 English and 139 Chinese puzzles, and an augmented release expands that to 1,575 English and 883 Chinese puzzles. A proposed solution counts only when the verifier accepts it.
AutoLogi
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-4.1OpenAI, released 2025-04-14 | 88.2% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | - |
| Claude Opus 4Anthropic, released 2025-05-22 | 86.1% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | Effort: no extended thinking |
| Claude Sonnet 4Anthropic, released 2025-05-22 | 89.8% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | Effort: no extended thinking |
| Gemini 2.5 FlashGoogle, released 2025-05-20 | 84.1% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | - |
| DeepSeek-V3-0324DeepSeek, released 2025-03-24 | 88.9% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | - |
| Qwen3-235B-A22BAlibaba, released 2025-04-29 | 83.3% | Moonshot AI, Kimi K2 release pagechecked 2026-10-15 | Effort: non-thinking |
| Kimi K2 InstructMoonshot AI, released 2025-07-11 | 89.5% | Moonshot AI, Kimi K2 release pagechecked 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.