LLM Test - Pangram Substitution Puzzle

Test and benchmark large language models (LLMs) with our interactive pangram-substitution puzzle. Measure LLM reasoning, prompt handling, and problem-solving skills in real time with a browser-based AI evaluation tool that doubles as a fun logic game.

Jan 13, 2026 v0.1.1

Configure Settings

Make sure to pick a unique seed number to ensure the LLM has not already solved the puzzle.

Current Levels Value:
Decimal: 0
Binary: 00000
Hex: 0x0
Active Levels:
No Levels selected

Check The Answer





The quick fox pangram lookup test. Create a language that maps real words to
words within the target word list. Then ask the LLM to figure out the
sentence and then fill in the missing word(s).
MakeLevel
ChatGPT4+1
5+2
5.1+0
Gemini2+1
2.5+2
3+2
Grok4+3
Kimik2+3
MiniMaxM2.7+0
Sonnet4Unable-1
Levels measure the reasoning models. On auto setting (no super pro plans).
And score represents total reasoning capacity. It does not measure cost. It also does not account for extra computations; while some models may have access to tools, others may not. Test results were taken via the chat app interface.
Email llmtest@snowdon.dev to sign
up to the newsletter containing periodic results.