Microsoft Researchopen-weight
Released: 2021-04-13

HMNet (gold spans) (paper Table 3 R-1)

AI Model evaluated in benchmark studies from Microsoft Research.

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
QMSumNearing Saturation36.06%
65
2021-04-13independentSource ↗
Local Hardware Execution (Ollama)Hardware Compatible
# 1. Pull and execute model locally with Ollama
ollama run hmnet-gold-spans-paper-table-3-r-1

# 2. Or invoke via local OpenAI-compatible endpoint
curl http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hmnet-gold-spans-paper-table-3-r-1",
    "messages": [{"role": "user", "content": "Analyze reasoning chains on AIME 2026"}]
  }'

Evaluation & Sourcing Notes

Scores listed for HMNet (gold spans) (paper Table 3 R-1) 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.