A refreshed terminal task suite repairs environment and instruction issues from the earlier release.
102 model results
One row per model and compatible score measure. Mean = equal-weight arithmetic average of imported reports. Distinct configurations reported for the same model in a source table remain separate. Reports can overlap; the range is not a confidence interval. Unbundle to inspect each observation.
Publisher-selected recent-model cohort from the public evaluation page. Model labels preserve effort and fallback configurations. Values are a dated snapshot, not a live feed. Consult the publisher’s methodology for the harness, task split and judging; do not merge this cohort with vendor-run results.
Public source leaderboard captured 26 October 2026. Model names, configurations, native score units and source-reported uncertainty are retained. Version and task split follow this specific Vals methodology page. These are published observations, not evaluations run by RLTasks.
TRACE THE SCORE · Per-model notes use published breakdowns where available.
Score vs. cost per test
Vals AI · 70 observations
Terminal-Bench 2.1 · Score · higher is better
Costs are Vals AI’s published Cost / Test in USD, paired with the score from the same result. They reflect that evaluation’s workload and configuration; they are not token prices or cost per successful task. Missing costs are omitted. Explore all reported results ↓
The dashed line traces the best observed score as reported cost increases. It describes this selection of reports, with their original configurations. It does not estimate unmeasured models or costs.
View plotted values and sources (70)
Terminal-Bench 2.1 · Terminal-Bench 2.1 · Score. Published measurements in their original score units.
A refreshed terminal task suite repairs environment and instruction issues from the earlier release.
How to read the result
Keep this version for historical comparisons and regression studies under a pinned environment.
Limits and comparison traps
The refreshed verifiers can change outcomes. Label both task-set and harness versions instead of calling every release Terminal-Bench.
Published evaluation
The linked publication documents the task and scoring procedure. Model results retain the source’s evaluation setting, native score units and available uncertainty.
Where this fits in an evaluation suite
The agent wrapper is part of the system. Pin tools, dependencies, timeouts, tests, and the repository revision. Compare contest coding separately from repository maintenance.
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
Use the exact implementation, version, task subset, tool access, attempt budget, and judge described by the 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.