agents benchmark
Meta Internal Coding Bench
Meta's internal evaluation of coding-agent performance.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
Meta Internal Coding Bench Ranking
Higher score ranks better on this benchmark.
| 01 | ME | 70.6% | 100.0% | 1 | C |
Meta Internal Coding Bench Highlights
The leading models and scores on this benchmark.
What is Meta Internal Coding Bench?
What Meta Internal Coding Bench measures and how its scores work.
Meta's internal evaluation of coding-agent performance.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Meta Internal Coding Bench
- Modality
- text
- Primary category
- agents
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- meta-internal-coding-bench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Meta Internal Coding Bench.
Which model scores highest on Meta Internal Coding Bench?
Muse Spark 1.2 is currently ranked first with 70.6%.
What does Meta Internal Coding Bench measure?
Meta's internal evaluation of coding-agent performance.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.