MBPP+activeCoding
MBPP+: Mostly Basic Programming Problems+
Metric: Pass@1 (higher is better)Introduced: 2023
MBPP+ extends MBPP with 21.2 average test cases per problem, a 35x increase over the original for more rigorous code generation evaluation.
Models ranked
5
tracked on this benchmark
Score band
79.4 – 76.0
best → lowest tracked
Snapshot trend
—
need ≥2 snapshots
Leaderboard
Tracked models ranked by Pass@1 (higher is better).
#Model variant and provenanceRelative to leaderScore
1
Qwen2.5-Coder-32B-Instruct
79.4Version: Not recordedHarness: Not recordedEvaluator: Not recordedObserved: May 28, 2026Confidence: Not recordedSource
2
Claude 3.5 Sonnet
78.8Version: Not recordedHarness: Not recordedEvaluator: Not recordedObserved: May 28, 2026Confidence: Not recordedSource
3
GPT-4o (05-13)
78.0Version: Not recordedHarness: Not recordedEvaluator: Not recordedObserved: May 28, 2026Confidence: Not recordedSource
4
Llama 3.1 405B
77.5Version: Not recordedHarness: Not recordedEvaluator: Not recordedObserved: May 28, 2026Confidence: Not recordedSource
5
DeepSeek V3
76.0Version: Not recordedHarness: Not recordedEvaluator: Not recordedObserved: May 28, 2026Confidence: Not recordedSource
How to read this benchmark
This benchmark scores models where higher is better. Use scores for directional filtering and shortlisting, not universal quality ranking; then validate pricing, context window, provider availability, and fit for your workload.
Trust this score when
- There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
- The model list covers the same version family you can actually deploy today.
- Top candidates overlap with your required routing and feature requirements.
Be cautious when
- There is only one benchmark snapshot or the dataset appears stale.
- The benchmark metric direction is opposite of your decision objective.
- The score difference between options is narrow and likely within implementation variance.
Related benchmarks
Last reviewed: Apr 15, 2026