Date-bounded contest problems test coding and related code-repair or execution skills.
164 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.
Published observations span 2.83 percentage points. Configuration and source differences contribute to this spread; it is not measured run-to-run uncertainty.
#14 of 164 in this displayed comparison; 3.56 pp below the leader.
Published observations span 4.06 percentage points. Configuration and source differences contribute to this spread; it is not measured run-to-run uncertainty.
#22 of 164 in this displayed comparison; 4.25 pp below the leader.
Published observations span 4.12 percentage points. Configuration and source differences contribute to this spread; it is not measured run-to-run uncertainty.
#31 of 164 in this displayed comparison; 5.01 pp below the leader.
Published observations span 0.28 percentage points. Configuration and source differences contribute to this spread; it is not measured run-to-run uncertainty.
#32 of 164 in this displayed comparison; 5.11 pp below the leader.
Published observations span 1.36 percentage points. Configuration and source differences contribute to this spread; it is not measured run-to-run uncertainty.
#47 of 164 in this displayed comparison; 6.52 pp below the leader.
Published observations span 2.8 percentage points. Configuration and source differences contribute to this spread; it is not measured run-to-run uncertainty.
#48 of 164 in this displayed comparison; 6.54 pp below the leader.
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.
Earlier-2026 baseline cohort from the official model card. Asterisks identify competitor scores re-evaluated by Kimi rather than cited from their reports. Coding scores average ten runs; vision averages three runs. Tool-enabled and no-tools results, F1 and exact accuracy, pass@3 and pass^3 remain separate rows. MCPMark here predates the Verified default. APEX uses 452 public tasks.
Earlier-2026 baseline comparison from the official Qwen model card. Original model labels and score formatting are retained. Language and vision tables use different Qwen reference models. Tools, image inputs, agent scaffolds and task subsets can differ; follow the model card’s evaluation details. Video-MME subtitle settings and HLE tool settings stay in separate rows. Original MCP-Mark results predate MCPMark Verified.
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.
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.
Date-bounded contest problems test coding and related code-repair or execution skills.
How to read the result
The problem date window is a central part of the result. Prefer a common window when comparing model families.
Limits and comparison traps
Freshness reduces some contamination risks; it does not prove a training-data exclusion. Pin release and evaluation dates.
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.