LLM Reference
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. High benchmark score alone doesn't make a model the right pick — weigh it against pricing, API availability, and release date.

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).

Compare candidates
#Model variant and provenanceScore
1
Qwen2.5-Coder-32B-Instruct
Version: Not recordedHarness: Not recordedEvaluator: Not recordedObserved: May 28, 2026Confidence: Not recordedSource
79.4
2
Claude 3.5 Sonnet
Version: Not recordedHarness: Not recordedEvaluator: Not recordedObserved: May 28, 2026Confidence: Not recordedSource
78.8
3
GPT-4o (05-13)
Version: Not recordedHarness: Not recordedEvaluator: Not recordedObserved: May 28, 2026Confidence: Not recordedSource
78.0
4
Llama 3.1 405B
Version: Not recordedHarness: Not recordedEvaluator: Not recordedObserved: May 28, 2026Confidence: Not recordedSource
77.5
5
DeepSeek V3
Version: Not recordedHarness: Not recordedEvaluator: Not recordedObserved: May 28, 2026Confidence: Not recordedSource
76.0

How to read this benchmark

This benchmark scores models where higher is better. Scores are useful for directional filtering and shortlisting — not for universal quality ranking. Prefer benchmarks closest to your workload, then validate the linked model pages for pricing, context window, and provider availability.

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.

FAQ

What does the MBPP+ benchmark measure?

MBPP+ extends MBPP with 21.2 average test cases per problem, a 35x increase over the original for more rigorous code generation evaluation. On this page it lists 5 tracked model variants where higher is better.

Is a higher Mostly Basic Programming Problems+ score always better?

For this benchmark, higher is better. A high score helps you shortlist, but confirm pricing, context window, and provider availability on each model page before committing — the top scorer is not always the right pick for your workload or budget.

How current is this Mostly Basic Programming Problems+ data?

This benchmark was last reviewed on Apr 15, 2026. Re-check the linked model pages for the freshest provider and pricing detail.

Related benchmarks

Last reviewed: Apr 15, 2026