AI models that run where your data lives.
Hypereum designs and operates specialised AI models: a proprietary fleet powering Hivemind AX, and open releases anyone can verify. The first family is compliance. Every model is built to run in your jurisdiction, on your hardware.
The models that power Hivemind AX for UK/EU regulated work: a proprietary fleet, and one open release anyone can verify.
The fleet, by role.
Planner
Reads a mission brief and decomposes it into a dependency-ordered task plan. Each task carries its scope, the evidence it needs, and where it sits in the execution order. Executors pick the plan up from there.
mission in · dependency-ordered task plan out
Executors
Perform the compliance analysis task by task, against the supplied evidence. Each task returns findings with severity, remediation effort, and the regulatory references they rest on. Raw executor output flows to the synthesizer, never straight to the report.
task + evidence in · findings, severity, regulatory refs out
Synthesizer
Takes every executor finding for a mission and aggregates it into mission-level risk. It resolves overlaps between tasks and weighs severity across the whole mission. What leaves this stage is the view a reviewer reads.
executor output in · mission-level risk out
Evaluator
Scores the quality of what the pipeline produces, finding by finding. Every score lands on a fixed schema, dimension by dimension, before anything is accepted. This is the one role we ship in the open: HivemindEval.
finding in · six-dimension scores out
Roles are stable. The models behind them are versioned, and rotate only through the gates below.
Five gates. Every release.
No fleet model reaches production without passing the acceptance gates published for HivemindEval: score variance across graded inputs, spread between quality tiers, strict tier ordering, and jurisdiction behavior checks.
Every number on this site follows one rule: it goes public only when anyone can recompute it. HivemindEval's results qualify, because the weights, the benchmark subset, every model's raw predictions and the scoring code are all open. Our proprietary fleet models pass the same internal gates before release, but their results descend from a validation apparatus we still label provisional, and there is no public benchmark on which you could rerun them. Publishing those numbers would be marketing, not measurement. The same standard will govern anything we publish in the future.
HivemindEval: the open proof point.
Our evaluator is open-weight. So is the benchmark. So are every model's raw predictions. Check us.
Format validity, before judgment quality.
Same hardware. Same prompt class. Format reliability is what the fine-tuning buys, reported separately from judgment quality, on purpose.
Five models, one benchmark.
If your primary need is defect detection rather than quality ranking, a rubric-prompted model is currently the better tool.
| Class | HivemindEval v2.1 | Qwen3-8B (rubric) |
|---|---|---|
| wrong_jurisdiction | 0.90 | 1.00 |
| hallucinated | 0.67 | 0.59 |
| missing_requirement | 0.42 | 0.65 |
| band_edge | 0.36 | 0.60 |
The format-reliability story versus the base model lives in the strip above. On the full board, the 72B rubric model also reaches 212/212.
95% confidence intervals overlap across all 5 models on this board; no interval is fully separated from another's.
If your primary need is defect detection rather than quality ranking, a rubric-prompted model is currently the better tool.
| Model | Tier concordance (95% CI) | Kendall τ | Defect separation | Schema-valid |
|---|---|---|---|---|
| Qwen2.5-72B-Instruct-AWQ (rubric) | 0.985 (95% CI [0.977–0.993]) | 0.801 | 0.602 | 212/212 |
| HivemindEval v2.1 (native) | 0.984 (95% CI [0.973–0.993]) | 0.817 | 0.591 | 211/212 |
| Qwen3-8B (rubric) | 0.973 (95% CI [0.959–0.985]) | 0.751 | 0.709 | 208/212 |
| Llama-3.3-70B (rubric) | 0.965 (95% CI [0.950–0.980]) | 0.764 | 0.616 | 173/212 |
| Qwen3-8B (native prompt, no fine-tune) | – | – | – | 0/212 |
| Model | Tier concordance (95% CI) | Kendall τ | Defect separation | Schema-valid |
|---|---|---|---|---|
| Qwen3-8B (rubric) | 0.991 (95% CI [0.977–1.000]) | 0.788 | 0.639 | 67/68 |
| Qwen2.5-72B-AWQ (rubric) | 0.990 (95% CI [0.980–1.000]) | 0.833 | 0.549 | 68/68 |
| HivemindEval v2.1 (native) | 0.979 (95% CI [0.958–0.998]) | 0.843 | 0.615 | 67/68 |
| claude-sonnet-5 (rubric) | 0.976 (95% CI [0.951–0.996]) | 0.777 | 0.562 | 66/68 |
| Llama-3.3-70B (rubric) | 0.964 (95% CI [0.932–0.988]) | 0.798 | 0.667 | 56/68 |
Check it yourself.
$ python3 eval/score_benchmark.py
⟩ recomputes every CORE-68 cell, bit for bit, seed 7, no GPU
Every CORE-68 number is recomputable offline from published data. The full 212-item set is withheld and committed by hash above.
Sovereign deployment.
Frontier-class verifier output. Data that never leaves your jurisdiction. Hardware you own.
24 GB deployment is single-stream with minimal headroom; use a larger card for concurrency.
Verifier quality is provisional; see the benchmark above .
Get in touch