Back to leaderboard

Fireworks AI

Same Inference task · View

#2 in Inference

83B

Agent performance

Eval score
76%
Task success
Passed
Cost per runLower is better
$0.2194
Tool callsLower is better
11
ErrorsLower is better
1
RuntimeLower is better
1m 12s
Tokens usedLower is better
248,256

Discoverability

Discovery score
100%
Context7
llms.txt
MCP Server
Typed SDK
OpenAPI
Agent Skills

Eval details

Integration task
# Task Using https://docs.fireworks.ai, complete the following task: Using Fireworks AI, build me a script that extracts structured data from this invoice and returns JSON: ---...
Generated files
1
Trace tool calls
11
Completed
9/23/2026
Stderr
None captured
Full eval