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

Update notices

A note when a benchmark one of your indexes uses gets a new version, with a one-click upgrade.

Benchmarks · Coding · Agents & computer use

LongTail-SWE: Haskell

LongTail-SWE's Haskell tasks: fix real GitHub issues in Haskell projects. The share of attempts that pass the tests.

11 models · 11 results · data as of 2026-11-18 · longtail-swe.com ↗

Leaderboard

GPT-6.1 Sol high

All results

11 rows
#ModelEffortLongTail-SWE: HaskellHarness
1GPT-6.1 Solhigh95.2%SWE-agent-like scaffold
2Kimi K3.1max95.2%SWE-agent-like scaffold
3Opus 5.5high92.9%SWE-agent-like scaffold
4DeepSeek V4.1 Flash 1017max85.7%SWE-agent-like scaffold
5GPT-5.6 Lunaxhigh83.3%SWE-agent-like scaffold
6GPT-5.6 Solhigh83.3%SWE-agent-like scaffold
7Kimi K3max83.3%SWE-agent-like scaffold
8DeepSeek V4 Flashhigh78.6%SWE-agent-like scaffold
9GLM 5.3 Flashmax66.7%SWE-agent-like scaffold
10Qwen 3.8 27Bxhigh52.4%SWE-agent-like scaffold
11Qwen 3.6 27Bmax26.2%SWE-agent-like scaffold