Interaction BenchInteraction Bench
v0.1 preview
LeaderboardEnvironmentsTasksPipelineMethodologyDocsBlogAboutContributors
Github
Snipe-IT

Snipe-IT

IT & infrastructure
IT asset and license tracking
Githubgrokability/snipe-it15.1k
Tech stack
PHPLaravelLivewireMySQL
Languages
PHP93.1%
Blade5.6%
Other1.3%
Available tools
Browser
Terminal
Network
Show a room’s complete location ancestry
Show a room’s complete location ancestry

Tasks

All 1 task
Show a room’s complete location ancestry
#18872 · Base 1c19850
Find where a room is located.
33%

Model results

Full leaderboard
Model
Harness
DeepSeek
DeepSeek Flash
DSH
33.9M in · 175.5k out · 34.0M total
DSH · 132 steps · $0.28 · 20m 27s · 34.0M tokens
DSH
132
$0.28
20m 27s
33.9M
175.5k
34.0M
OpenAI
GPT-6 Astra
Codex
1.5M in · 6.7k out · 1.5M total
Codex · 30 steps · $2.58 · 7m 53s · 1.5M tokens
Codex
Codex
30
$2.58
7m 53s
1.5M
6.7k
1.5M
Z.ai
GLM-5.3 Flash
ZCode
37.8M in · 82.7k out · 37.9M total
ZCode · 334 steps · $1.22 · 1h 02m · 37.9M tokens
ZCode
334
$1.22
1h 02m
37.8M
82.7k
37.9M
Claude
Claude Opus 5.5
Claude Code
5.7M in · 25.3k out · 5.7M total
Claude Code · 83 steps · $2.43 · 8m 46s · 5.7M tokens
Claude Code
Claude Code
83
$2.43
8m 46s
5.7M
25.3k
5.7M
Qwen
Qwen3.8 Max
Codex
20.8M in · 81.5k out · 20.8M total
Codex · 207 steps · $6.18 · 58m 46s · 20.8M tokens
Codex
Codex
207
$6.18
58m 46s
20.8M
81.5k
20.8M
MoonshotAI
Kimi K3
Kimi Code
20.7M in · 63.6k out · 20.8M total
Kimi Code · 212 steps · $7.60 · 1h 02m · 20.8M tokens
Kimi
Kimi Code
212
$7.60
1h 02m
20.7M
63.6k
20.8M
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