Skip to content
agentboards
Compare/mini-SWE-agent vs Mistral Vibe

mini-SWE-agentvsMistral Vibe

Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.

mini-SWE-agent
SWE-agent (Princeton and Stanford) · Terminal agent
#8OSS
Panel
6.9
1 spec wins
Reliability
6.3
Usefulness
5.5
Cost
8.8
Longevity
7.0

“One hundred lines of Python, which is fewer than most competitors spend on their pricing page.”

Mistral Vibe
Mistral AI · Terminal agent
#19OSSMCP
Panel
6.5
2 spec wins
Reliability
6.2
Usefulness
6.3
Cost
7.3
Longevity
6.3

“Students pay $5.99 a month, the first coding agent priced like a student streaming plan.”

Spec by spec

Specmini-SWE-agentMistral Vibe
Architecture
CategoryTerminal agentTerminal agent
Runslocal, sandboxlocal, cloud, sandbox
Platformsmacos, linuxmacos, linux, windows
Context windownot documentednot documented
Protocols
MCP clientNoYes
MCP serverNoNo
Capabilities
Runs terminal commandsYesYes
Multi-file editsYesYes
Git operationsYesYes
Browser controlNoNo
Sandboxed executionYesYes
Multi-agent orchestrationNoYes
Headless / CI modeYesYes
Models
Backboneany via litellmDevstral 2, Devstral Small 2, Mistral Medium 3.5
Bring your own modelYesYes
Local modelsYesYes
Cost
Pricing modelbyokmixed
Starts atn/a$14.99/mo
Free tierYesYes
Bring your own keyYesYes
Openness
Open sourceYesYes
LicenseMITApache-2.0
GitHub stars8,4105,102

Which one would each critic pick

Criticmini-SWE-agentMistral VibePick
El Juez——not enough reviews
El Amigo6.86.8no preference
El Crítico6.56.0mini-SWE-agent — There is no procedure for anything beyond a shell command, opening a pull request is tell the LM to figure it out, and without a sandbox flag every command lands on the host.
El Profesor8.06.0mini-SWE-agent — The reference harness for the SWE-bench bash-only leaderboard: one bash action per turn via subprocess.run, a linear history, no tool-calling API, and Gemini 3 Pro reported above 74% on Verified.
La Inversora6.86.3mini-SWE-agent — No company, a Princeton and Stanford lab with 6,938 stars; the funding is grants and the exit is a paper, which is more stable than half the cap tables on this board.
La Jefa5.06.3Mistral Vibe — Team is $24.99 per user, $1,499.40 a month for sixty, and Enterprise is custom, which is the phrase that adds a quarter to procurement.
El Hacker8.58.0mini-SWE-agent — MIT, any model through litellm, OpenRouter or Portkey including my local server, a YAML config, and source short enough to read before breakfast; the missing MCP client is the only gap.

Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.

Want a third column? The compare tool handles any two agents. Three-way comparisons are on the roadmap once the spec rows are all verified.
↑↓ navigate · Enter open · Esc close589 agents + guides