Meta AIopen-weight
Released: 2021-02-09

RoBERTa encoder (CodeSearchNet summarization, six-language overall BLEU)

AI Model evaluated in benchmark studies from Meta AI.

Intelligence Index
—/ 100
Calibrated multi-domain composite
Throughput Speed
—tok/sec
Output streaming throughput
Time To First Token
—ms
Initial chunk server latency
LiveBench Contam-Free
—%
September 2026 suite score

Sourced Benchmark Evaluations (1)

Verified performance across authoritative benchmarks with provenance tracking.
BenchmarkStatusScoreTrustDateSource TypeProvenance
CodeXGLUEDeprecated16.57%
20
2021-02-09independentSource ↗
Local Hardware Execution (Ollama)Hardware Compatible
# 1. Pull and execute model locally with Ollama
ollama run roberta-encoder-codesearchnet-summarization-six-language-overall-bleu

# 2. Or invoke via local OpenAI-compatible endpoint
curl http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "roberta-encoder-codesearchnet-summarization-six-language-overall-bleu",
    "messages": [{"role": "user", "content": "Analyze reasoning chains on AIME 2026"}]
  }'

Evaluation & Sourcing Notes

Scores listed for RoBERTa encoder (CodeSearchNet summarization, six-language overall BLEU) represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.

All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.