Toolathlon

Reported in recent model launches

These model reports include this benchmark. Their harnesses, task subsets, scoring policies, and resource budgets can differ; follow each report’s evaluation notes before joining the numbers.

What it measures

Long-horizon tasks require coordinating tools and completing a practical workflow.

How to read the result

Follow the chain from the user’s request to the verified result. Tool-call validity alone does not establish that the requested work was completed.

Limits and comparison traps

Task and service versions, tool permissions, action budgets and resets must be pinned. Model-launch scores can use different agent scaffolds.

Benchmark reference notes

Long-horizon multi-tool orchestration benchmark reported in Kimi K2.6.

Where this fits in an evaluation suite

A transcript that says “done” is weaker evidence than the verified final state. Track policy violations, recoveries, and invalid attempts alongside success.

Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.

A reproducible comparison

Pin the benchmark release, task split, model configuration, tools, sampling budget, and evaluation harness described by the primary source.

Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.