Support

Settings

Theme

Explore themes

Mode

Library

Looks borrowed from benchmark sites and products. Themes with a light and a dark version follow your mode.

Bring your own theme

Upload a Priors theme file, or have your agent make one: copy the prompt, tell it the look you want, and upload what it returns. With the Priors skill installed it already knows the format.

Custom themes stay in this browser. They travel inside shared chart links and a page's theme, so others see them as you do.

For the builder, Explore and model pages on this device. Published pages keep the theme their owner picked.

Mode

Benchmarks · reasoning

LLM2014 Logic

A private, monthly-rotating bank of about 28 logic and reasoning questions (interleaved text, rule induction, log analysis, puzzles), three runs each; the derivation must be correct, guesses earn nothing. Median score out of 100.

26 models · 27 results · updated 2026-11 · llm2014.github.io ↗

Leaderboard

Chart settings
26 of 26 selected
GPT-6 Astra xhigh

More from this benchmark

3 published measures

All results

27 rows
#ModelEffortLLM2014 LogicTimeOutput tokens
1GPT-6 Astraxhigh86.55.2 min13k
2Opus 5.5xhigh77.74.9 min33k
3Fable 5.1xhigh70.58.0 min41k
4Gemini 4 Argonhigh69.17.5 min24k
5GPT-6.1 Solxhigh67.810 min13k
6Kimi K3.1max61.622 min51k
7Muse Wonder (Max)xhigh59.611 min54k
8Sonnet 5.5xhigh57.46.1 min40k
9DeepSeek V4.1 Flash 1017max56.09.9 min77k
10Grok 4.7xhigh52.524 min81k
11MiniMax M3.1max51.812 min53k
12Gemini 3.8 Flashhigh51.36.5 min37k
13GLM 5.3max47.726 min68k
14DeepSeek V4 Pro 0813max47.428 min62k
15Qwen 3.8 Maxxhigh45.327 min72k
16GLM 5.3 Flashmax44.622 min51k
17Qwen 3.8 Flashxhigh37.617 min68k
18Haiku 5.5xhigh32.35.3 min59k
19Qwen 3.8 27Bxhigh31.238 min73k
20Hy3high28.119 min48k
21Ling 3.1 Flashxhigh25.117 min88k
22GPT-6 Lunaxhigh23.95.7 min28k
23Gemini 3.5 Flash-Litehigh11.93.1 min16k
24GPT-5.5 Instant9.448s1.9k
25Mistral Large 4high6.49.3 min28k
26DeepSeek V4.1 Flashmax3.429s3.6k
27Qwen 3.8 27Bmax2.93.7 min8.1k