fetching harness data...
Same model, different harnesses, very different results. The harness owns context curation, tool design, retry policy, and verifier integration, so the same model can sit several points apart depending on which scaffold calls it, and the gap column below is the live measure of that. This page tracks the harness gap as a first-class number. Every row is an upstream Terminal-Bench row with its 95% confidence interval. We do not re-run benchmarks, and no vendor headline figure is promoted into the score column. Note that the two revisions are not comparable: 4.0 is the current and much harder board, 2.1 is the older and largely saturated one.
The harness is the agent scaffold that wraps a base language model: the system prompt, the tools, the file-edit format, the retry and verifier loop, the context-management strategy, and the way errors are surfaced back to the model.
GET /api/harnesses
?view=summary for the current-board ranking and biggest harness gaps,
?view=gaps for full harness-gap analysis,
?view=combined for the current board normalized to its top score,
or no param for the raw benchmark graph.
12-hour cache. CORS enabled. No auth, no key, no signup.
tf_harnesses via /api/mcp and
as a function-calling tool definition at /api/llm-tools.