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

500 software tasks built from work Ramp's engineers shipped to production, each model running in its lab's own coding harness at high reasoning effort. Share resolved in a single attempt, with web tools off.

16 models · 16 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. 2 more models under All models in settings.

More from this benchmark

2 published measures

All results

16 rows
#ModelEffortRamp SWE-Bench v2Subscription $ / taskAPI $ / taskTimeOutput tokensHarness
1GPT-6.2 Astrahigh76.4% ±3.7$0.22$3.316.6 min9.6kcodex
2Gemini 4 Carbonhigh75.4% ±3.8$0.26$4.2556 min72kopencode
3Fable 5.2high73.4% ±3.9$0.14$3.7920 min31kclaude-code
4GPT-6.2 Solhigh73.4% ±3.9$0.035$1.057.5 min11kcodex
5Gemini 4 Hydrogenhigh71.6% ±3.9$0.086$2.1124 min48kopencode
6GPT-6.1 Terrahigh70.4% ±4.0$0.016$0.468.3 min16kcodex
7Opus 5.5high67.8% ±4.1$0.020$1.5315 min16kclaude-code
8Grok 4.7high64.4% ±4.2$0.30$4.3220 min51kgrok-build
9GPT-6 Astrahigh63.4% ±4.2$0.19$5.228.3 min15kcodex
10Sonnet 5.5high63.2% ±4.2$0.006$0.4710 min11kclaude-code
11DeepSeek V4.1 Flash 1017high60.8% ±4.3free$0.2219 min40kdeepseek-harness
12GPT-6.1 Solhigh59.6% ±4.3$0.025$0.748.0 min16kcodex
13Muse Wonderhigh58.6% ±4.3$3.06$4.5917 min39kmuse-code
14Haiku 5.5high57.4% ±4.3$0.005$0.2814 min36kclaude-code
15GPT-6 Lunahigh52.4% ±4.4$0.005$0.0719.5 min28kcodex
16Muse Emberhigh51.8% ±4.4$0.11$0.1114 min42kmuse-code