agents benchmark
Meta Internal Coding Bench Leaderboard
Meta Internal Coding Bench is Meta's internal evaluation of coding-agent performance.
Updated Sep 5, 2026
Models1
Model coverage1
MetricScore
EvidenceB
Meta Internal Coding Bench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelME | Score70.60% | Percentile100.00% | Participants1 | EvidenceC | Evaluated |
Meta Internal Coding Bench Highlights
The leading models and scores on this benchmark.
The Top AI Models for Meta Internal Coding Bench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis meta internal coding bench AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01MEMeta
- Score
- 70.60%
- Price
- $1.3 input / $4.3 output per 1M tokens
- Speed
- Up to 28.44 tok/s via Meta Model API
Strengths
- Ranks #1 of 1 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures Meta Internal Coding Bench, not total model capability
Selection summary
Best AI Models for Meta Internal Coding Bench
Muse Spark 1.2 currently leads Meta Internal Coding Bench with 70.60%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is Meta Internal Coding Bench?
What Meta Internal Coding Bench measures and how its scores work.
Meta Internal Coding Bench is a benchmark for evaluating coding-agent performance.
It measures coding-agent performance using Score reported as a ratio.
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
- overall
LLM Stats. 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 70.60%.
What are the top three models on Meta Internal Coding Bench?
The current leaders are Muse Spark 1.2 (70.60%).
Which Meta Internal Coding Bench model has the lowest official input price?
Muse Spark 1.2 has the lowest matched official input price at $1.3 input / $4.3 output per 1M tokens.
Which models are fastest among Meta Internal Coding Bench results?
The fastest matched records are Muse Spark 1.2 (28.44 tok/s via Meta Model API).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.