priors
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 · coding

DeepSWE v1

Original DeepSWE leaderboard: pass@1 on 113 long-horizon SWE tasks with mini-swe-agent. Used as fallback for models not yet run on v1.1.

21 models · 29 results · data as of 2026-10-29 · deepswe.datacurve.ai ↗

Leaderboard

Chart settings
21 of 21 selected
GPT-5.5 xhigh

Score vs subscription cost per task

DeepSWE v1 · measured cost per task · subscription-priced where plan data exists (Real API Pricing, full allowance used)

Highlight models

Click a point on the chart to highlight that exact effort; click it again to remove it.

14 more in settings
Chart settings
21 of 21 selected

More from this benchmark

3 published measures
Agent steps per task29 results · lower is better

Highlight models

Click a point on the chart to highlight that exact effort; click it again to remove it.

14 more in settings
Chart settings
21 of 21 selected
Time per task29 results · lower is better
Output tokens per task29 results · lower is better

All results

29 rows
#ModelEffortDeepSWE v1Subscription $ / taskAPI $ / taskAgent stepsTimeOutput tokensHarness
1GPT-5.5xhigh70.0% ±2.8$0.36$6.617921 min47kmini-swe-agent
2GPT-5.5high61.9% ±3.6$0.25$4.475815 min31kmini-swe-agent
3Opus 4.8max58.2% ±2.3$0.22$1310843 min136kmini-swe-agent
4Opus 4.8xhigh57.7% ±4.0$0.13$7.558732 min86kmini-swe-agent
5GPT-5.4xhigh55.5% ±2.2$4.38$4.386927 min71kmini-swe-agent
6Opus 4.7max54.2% ±4.7$18$1820339 min103kmini-swe-agent
7Opus 4.8high50.7% ±3.0$0.069$3.986620 min48kmini-swe-agent
8GPT-5.5medium48.0% ±2.9$0.13$2.34429.8 min19kmini-swe-agent
9Opus 4.8medium47.3% ±3.9$0.056$3.256019 min40kmini-swe-agent
10Opus 4.7xhigh44.7% ±2.9$8.58$8.5812624 min66kmini-swe-agent
11GLM 5.2max41.5% ±2.9$0.34$3.9512544 min82kmini-swe-agent
12Opus 4.7high40.3% ±3.5$4.83$4.838717 min46kmini-swe-agent
13Sonnet 4.6high31.8% ±1.9$5.52$5.5212942 min76kmini-swe-agent
14Opus 4.7medium31.6% ±4.0$2.34$2.345510 min27kmini-swe-agent
15Gemini 3.5 Flashmedium28.3% ±3.5$7.42$7.427517 min189kmini-swe-agent
16Opus 4.6max27.6% ±3.7$5.39$5.3910330 min44kmini-swe-agent
17GPT-5.4 Minixhigh24.3% ±3.0$2.08$2.088633 min135kmini-swe-agent
18Kimi K2.6max23.9% ±2.5$3.16$3.1614756 min84kmini-swe-agent
19MiniMax M3max20.4% ±3.7$0.94$5.5731457 min98kmini-swe-agent
20MiMo V2.5 Proxhigh19.5% ±1.9$0.13$1.9912128 min49kmini-swe-agent
21Qwen 3.7 Maxmax17.7% ±1.4$0.64$2.1211017 min42kmini-swe-agent
22GLM 5.1max17.5% ±0.8$7.46$7.4617735 min49kmini-swe-agent
23Grok Build 0.113.1% ±2.4$6.60$6.6017644 min52kmini-swe-agent
24Gemini 3.1 Prohigh9.7% ±2.8$1.84$1.847436 min53kmini-swe-agent
25DeepSeek V4 Promax7.5% ±2.7$0.70$4.2211137 min50kmini-swe-agent
26Gemini 3 Flashhigh5.1% ±2.5$1.53$1.537139 min233kmini-swe-agent
27Qwen 3.6 Plusmax2.7% ±1.2$4.25$4.2516435 min67kmini-swe-agent
28Haiku 4.5xhigh0.2% ±0.3$0.84$0.841099.2 min39kmini-swe-agent
29MiniMax M2.7high0.2% ±0.3$0.13$0.7013635 min60kmini-swe-agent