Benchmark Almanac

InternLM

We track 2 benchmarks that InternLM made or helped make.

1 in use 2 with public code 2 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
WildClawBench 60 original in-the-wild tasks run inside a live OpenClaw assistant environment, chaining 10-60+ tool calls. Scored by task-level graders. General assistants Mar 2026 67.2% In use
InternBootcamp Models solve generated reasoning tasks with task-specific answer checkers. The hub port lets users select a task and sample examples with a fixed seed. Language reasoning May 2025 55.7 Not in cards