Interaction BenchInteraction Bench
v0.1 preview
LeaderboardEnvironmentsTasksPipelineMethodologyDocsBlogAboutContributors
Github
Hoppscotch

Hoppscotch

Developer tools
API client for REST, GraphQL and realtime requests
Githubhoppscotch/hoppscotch80.7k
Tech stack
VueTypeScriptNestJSPostgreSQL
Languages
TypeScript68.5%
Vue23.5%
Rust3.5%
JavaScript3.3%
Other1.2%
Available tools
Browser
Terminal
Network
Edit an environment variable from the tooltip on the request URL
Edit an environment variable from the tooltip on the request URL

Tasks

All 1 task
Edit an environment variable from the tooltip on the request URL
#6155 · Base a074039
Edit the site environment variable from the REST request URL.
17%

Model results

Full leaderboard
Model
Harness
OpenAI
GPT-6 Astra
Codex
1.8M in · 5.2k out · 1.8M total
Codex · 36 steps · $2.65 · 11m 39s · 1.8M tokens
Codex
Codex
36
$2.65
11m 39s
1.8M
5.2k
1.8M
DeepSeek
DeepSeek Flash
DSH
34.1M in · 74.5k out · 34.2M total
DSH · 171 steps · $0.37 · 27m 35s · 34.2M tokens
DSH
171
$0.37
27m 35s
34.1M
74.5k
34.2M
Z.ai
GLM-5.3 Flash
ZCode
29.7M in · 83.4k out · 29.8M total
ZCode · 252 steps · $0.97 · 1h 07m · 29.8M tokens
ZCode
252
$0.97
1h 07m
29.7M
83.4k
29.8M
MoonshotAI
Kimi K3
Kimi Code
3.3M in · 35.1k out · 3.3M total
Kimi Code · 27 steps · $1.82 · 22m 46s · 3.3M tokens
Kimi
Kimi Code
27
$1.82
22m 46s
3.3M
35.1k
3.3M
Claude
Claude Opus 5.5
Claude Code
4.9M in · 23.6k out · 4.9M total
Claude Code · 75 steps · $2.28 · 2h 06m · 4.9M tokens
Claude Code
Claude Code
75
$2.28
2h 06m
4.9M
23.6k
4.9M
Qwen
Qwen3.8 Max
Codex
10.9M in · 81.4k out · 11.0M total
Codex · 125 steps · $3.62 · 1h 05m · 11.0M tokens
Codex
Codex
125
$3.62
1h 05m
10.9M
81.4k
11.0M
Interaction BenchInteraction Bench

Benchmarked on what users feel.

// results

LeaderboardEnvironmentsTasks

// how it works

PipelineMethodologyDocsBlog

// project

AboutContributorsContact usGitHubReport an issue
$ ibench --release 0.1 --statuspreview · built by EvalSys