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

Ramp SWE-Bench v2 (Bash harness)

Ramp SWE-Bench v2's 500 production-derived tasks with every model in the same mini-swe-agent Bash harness, so the harness is held constant. Share resolved in a single attempt at high reasoning effort.

22 models · 22 results · updated 2026-11-17 · labs.ramp.com ↗

Leaderboard

GPT-6.2 Astra high

Score vs subscription cost per task

Highlight models

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

Heavy line: best score at each price. Thin lines join one model's effort levels. Cost uses each model's most subsidized plan, or API price with no plan data. 7 more models under All models in settings.

More from this benchmark

2 published measures

All results

22 rows
#ModelEffortScoreSubscription $ / taskAPI $ / taskTimeOutput tokensHarness
1GPT-6.2 Astrahigh75.0% ±3.8$0.068$1.038.2 min7.1kmini-swe-agent
2Gemini 4 Carbonhigh74.0% ±3.8$0.32$5.331.1 h74kmini-swe-agent
3Fable 5.2high73.0% ±3.9$0.24$6.4533 min63kmini-swe-agent
4GPT-6.2 Solhigh72.4% ±3.9$0.009$0.289.3 min8.1kmini-swe-agent
5Opus 5.5high71.2% ±4.0$0.013$0.9914 min14kmini-swe-agent
6Gemini 4 Hydrogenhigh70.8% ±4.0$0.071$1.7528 min47kmini-swe-agent
7Fable 5.1high63.8% ±4.2$0.38$2.4315 min18kmini-swe-agent
8GPT-6.1 Terrahigh60.6% ±4.3$0.005$0.137.6 min7.7kmini-swe-agent
9Muse Wonderhigh57.8% ±4.3$1.76$2.6516 min26kmini-swe-agent
10Sonnet 5.5high57.6% ±4.3$0.003$0.246.8 min6.8kmini-swe-agent
11Grok 4.7high55.4% ±4.4$0.27$3.9812 min18kmini-swe-agent
12Gemini 4 Argonhigh54.8% ±4.4$4.34$6.511.1 h92kmini-swe-agent
13GPT-6 Astrahigh54.6% ±4.4$0.060$1.699.5 min9.0kmini-swe-agent
14Muse Emberhigh54.4% ±4.4$0.064$0.06411 min29kmini-swe-agent
15DeepSeek V4.1 Flash 1017high53.4% ±4.4free$0.1616 min23kmini-swe-agent
16Haiku 5.5high52.8% ±4.4$0.002$0.1218 min27kmini-swe-agent
17GPT-6.1 Solhigh52.0% ±4.4$0.009$0.278.8 min9.1kmini-swe-agent
18Gemini 3.8 Flashhigh47.0% ±4.4$0.11$2.621.4 h81kmini-swe-agent
19Kimi K3.1high45.4% ±4.4$0.47$0.7011 min12kmini-swe-agent
20GPT-6 Lunahigh42.6% ±4.3$0.001$0.0194.1 min11kmini-swe-agent
21Beam 1.0high34.0% ±4.1$0.081$0.0817.8 min8.6kmini-swe-agent
22Nemotron 3.5 Super VLhigh12.0% ±2.8free$0.112.6 min12kmini-swe-agent