An agentic-coding evaluation appears alongside terminal and repository benchmarks in Anthropic’s release.
82 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.
Reported values are percentages except GDPval-AA, which is Elo. Tool-enabled and partial scores keep their labels. Effort settings, fallback models, and source-run protocols vary; see the original footnotes.
Epoch AI public data snapshot, CC BY 4.0. Externally collected result; original evaluation provider is linked. CSV: cursorbench_external.csv; score column: Score; fraction scale: 1. Model version is retained in configuration. Original source authors retain credit and any additional licensing terms.
TRACE THE SCORE · Per-model notes use published breakdowns where available.
Score vs. release date
Epoch AI · 78 observations
CursorBench · Score · % · higher is better
Dates are model release dates recorded by Epoch AI, not evaluation dates. Each point retains its published score and configuration. Separate releases are not a matched longitudinal experiment. Missing dates are omitted. Explore all reported results ↓
The dashed line traces the best observed score through the model release dates. It describes this selection of reports, with their original configurations. It does not estimate unmeasured models or costs.
View plotted values and sources (78)
CursorBench 4.0 · CursorBench · Score · %. Published measurements in their original score units.
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.
An agentic-coding evaluation appears alongside terminal and repository benchmarks in Anthropic’s release.
How to read the result
Treat its task distribution and coding environment as a specific slice of engineering work rather than a substitute for all code benchmarks.
Limits and comparison traps
The launch supplies a reported result. Pin the source and version, and avoid joining it to earlier CursorBench releases without a common evaluation contract.
Benchmark reference notes
Internal/launch benchmark measuring IDE code editing, multi-file composer workflows, and bug fixing (reported in Claude Opus 5.5).
Epoch data and evaluation setting
Epoch AI publishes this benchmark in its capability collection. Imported rows retain the published score column and model configuration. Original authors and evaluation providers remain credited in the result references.
Epoch attribution and score coverage
Data is attributed to Epoch AI under CC BY 4.0, with original evaluation providers credited in the linked source snapshots. Scores are imported only where a published mapping identifies the field and its scale; missing or incompatible records are omitted rather than assigned zero.
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
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.