LetTokenBurn
Sign in
Auto43%Harbor: pendingKnowledge & Reasoning

EnigmaEval

Tracked by Epoch AI's Benchmarking Hub (results collected from external sources).

PaperLeaderboardHomepage

How to run

ltb · enigmaeval
$ npm i -g lettokenburn-cli
$ ltb bench info enigmaeval

External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.

Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs

Scores

41 sourced entries
HarnessSourceConfidenceLink
Claude Fable 539.3N/AIndependentmediumN/Alabs.scale.com
GPT-5.6 Sol37.1N/AIndependentmediumN/Alabs.scale.com
Gemini 3.1 Pro36.8N/AIndependentmediumN/Alabs.scale.com
Gemini-3.5-flash25.4N/AIndependentmediumN/Alabs.scale.com
GPT-5.4 Pro23.8N/AIndependentmediumN/Alabs.scale.com
Claude Opus 4.823.5N/AIndependentmediumN/Alabs.scale.com
GPT-5 Pro (2025-10-06)18.8N/AIndependentmediumN/Alabs.scale.com
Gemini 3 Pro18.2N/AIndependentmediumN/Alabs.scale.com
GPT-5.416.0N/AIndependentmediumN/Alabs.scale.com
o313.1N/AIndependentmediumN/Alabs.scale.com
Claude Opus 4.5 (2025-11-01)11.9N/AIndependentmediumN/Alabs.scale.com
GPT-5.111.2N/AIndependentmediumN/Alabs.scale.com
GPT-510.5N/AIndependentmediumN/Alabs.scale.com
GPT-5.2-chat10.4N/AIndependentmediumN/Alabs.scale.com
o4-mini9.2N/AIndependentmediumN/Alabs.scale.com
GPT-5-mini8.2N/AIndependentmediumN/Alabs.scale.com
Claude Opus 4.67.6N/AIndependentmediumN/Alabs.scale.com
Claude Opus 4.1 (2025-08-05)7.2N/AIndependentmediumN/Alabs.scale.com
o1-pro-2025-03-196.1N/AIndependentmediumN/Alabs.scale.com
Claude Sonnet 4.5 (2025-09-29)6.0N/AIndependentmediumN/Alabs.scale.com
OpenAI/o1-2024-12-17-high5.7N/AIndependentmediumN/Alabs.scale.com
Claude Opus 4 (2025-05-14)5.6N/AIndependentmediumN/Alabs.scale.com
Gemini 2.5 Pro Preview 06-055.6N/AIndependentmediumN/Alabs.scale.com
Claude 3.7 Sonnet Thinking (2025-02-19)4.2N/AIndependentmediumN/Alabs.scale.com
Gemini 2.5 Pro Exp 03-254.1N/AIndependentmediumN/Alabs.scale.com
Kimi K2.53.4N/AIndependentmediumN/Alabs.scale.com
GPT-4.5 Preview (2025-02-27)3.2N/AIndependentmediumN/Alabs.scale.com
Claude Sonnet 4 (2025-05-14)3.1N/AIndependentmediumN/Alabs.scale.com
Gemini 3.1 Flash Lite3.0N/AIndependentmediumN/Alabs.scale.com
Gemini 2.5 Flash Preview 05-202.7N/AIndependentmediumN/Alabs.scale.com
Gemini 2.5 Pro Preview 05-062.4N/AIndependentmediumN/Alabs.scale.com
GPT-4.12.2N/AIndependentmediumN/Alabs.scale.com
Gemini 2.0 Flash Thinking Exp 01-211.1N/AIndependentmediumN/Alabs.scale.com
Claude 3.5 Sonnet0.9N/AIndependentmediumN/Alabs.scale.com
Pixtral Large 24110.8N/AIndependentmediumN/Alabs.scale.com
Claude 3 Opus0.8N/AIndependentmediumN/Alabs.scale.com
GPT-4o0.8N/AIndependentmediumN/Alabs.scale.com
Gemini 2.0 Pro Exp 02-050.7N/AIndependentmediumN/Alabs.scale.com
Gemini 2.0 Flash 02-050.6N/AIndependentmediumN/Alabs.scale.com
Llama-4-Maverick-17B-128E-Instruct0.6N/AIndependentmediumN/Alabs.scale.com
Llama-3.2-90B-Vision-Instruct0.4N/AIndependentmediumN/Alabs.scale.com

Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.

Reproduced by the community

All runs
Loading community runs…

About

Tracked by Epoch AI's Benchmarking Hub (results collected from external sources). Random baseline 0; score ceiling 1 (0–1 scale).