Weaveweave / evals
Get started ↗
agent evals

Which models actually hold up.

Transparent evidence for how models perform inside Weave's multi-agent orchestration. Every run is reproducible, every case is inspectable, and every metric comes from real execution — no synthetic benchmarks, no cherry-picked demos.

RunAug 31, 2026, 05:40 PM UTC
Commite2f642ee
ModeProduction
DataSnapshot
Denominator

75 model-case evaluations covering 25 distinct test cases across 3 models and 8 capability suites. Each case was evaluated with each model.

Model × capability matrix

The central artifact: which models excel at which capabilities. Each cell is the pass rate for that model on that suite's cases.

Model
ModelLoom RoutingTapestry ExecutionShuttle ExecutionSpindle ToolsPattern PlanningWeft ReviewWarp SecurityTapestry Category RoutingOverall
GPT-5.5
OpenAI
100%100%100%50%50%100%50%0%48%
Claude Sonnet 4.5
Anthropic
100%100%50%50%50%50%100%0%44%
Claude Opus 4.5
Anthropic
67%100%50%50%50%50%100%0%40%

Capability suites

Each suite tests one orchestration capability. Aggregate pass rates show overall reliability; model-level detail reveals strengths and weaknesses.

Loom Routing

loom-routing

Tests delegation accuracy from Loom to specialist agents

9Evaluations
89%Pass rate
8/9Passed

Tapestry Execution

tapestry-execution

Verifies plan execution fidelity in Tapestry

6Evaluations
100%Pass rate
6/6Passed

Shuttle Execution

shuttle-execution

Tests domain specialist task completion

6Evaluations
67%Pass rate
4/6Passed

Spindle Tools

spindle-tools

Evaluates tool selection and usage accuracy

6Evaluations
50%Pass rate
3/6Passed

Pattern Planning

pattern-planning

Assesses plan quality and decomposition

6Evaluations
50%Pass rate
3/6Passed

Weft Review

weft-review

Tests code review quality and issue detection

6Evaluations
67%Pass rate
4/6Passed

Warp Security

warp-security

Validates security vulnerability detection

6Evaluations
83%Pass rate
5/6Passed

Tapestry Category Routing

tapestry-category-routing

Tests category-based task routing within Tapestry

30Evaluations
0%Pass rate
0/30Passed
Quality gate · allSuitesGreen

The allSuitesGreen flag is the strict suite gate emitted by the eval runner. One non-green suite makes the run false, regardless of overall pass rate.

Current status: false (33/75 evaluations passed — 44% overall pass rate).

Case-level evidence

Expand any case to see execution details. Pass means the case met all criteria. Partial is a quality annotation indicating incomplete success, and does not by itself determine the aggregate result. Fail means the case did not meet criteria.

Showing 1 representative row of 75 evaluations. View full report JSON ↗
Baseline and trends

This is an early production run, so historical trend data is sparse. Once multiple production runs accumulate, this section will show pass-rate trends over time, regression detection, and model performance evolution.

Methodology and context

All evaluations are produced by weave-io/weave and published in the weave-agent-evals repository. Each case is a real-world task scenario executed through Weave's orchestration layer.

Models are evaluated on identical cases to ensure fair comparison. Pass/fail is determined by automated verification of task completion, code correctness, and adherence to constraints.

Sanitized public reports are available in the data repository. View this run's report ↗