On August 4, 2026, Pokee AI shipped Pokee-Isaac 28B — a 28B-parameter, text-only agent foundation model built around a single thesis: run agents inside the customer's boundary, not against a cloud API. Its context window stretches to 10M tokens — and, more importantly, it produces usable scores at every measured length on the RULER long-context benchmark.

The most striking table in the technical report is RULER from 256K to 10M. Isaac returns 96.9, 96.7, 95.0, 95.8, 96.7, 93.3 — a usable score at every length. GPT-5.6 Luna on Azure holds up to 512K and context-overflows at 1M. Gemini 3.5 Flash Lite on Vertex AI scores 29.4 at 1M and zeros out beyond. Claude Haiku 4.5, Qwen 3.5 122B, and Nemotron 3 Super all hit 0.0 by 256K, except Nemotron's vendor-self-reported 91.75 at 1M — which was measured by NVIDIA, not Pokee, on the same installation. In other words, "usable at 10M" currently has exactly one implementation.

MRCR v2: the multi-needle gap widens to 0.3

MRCR v2 is the harder test: eight needles buried in long context, the model must retrieve and disambiguate a specified one. Isaac scores 0.607 / 0.743 / 0.500 at 256K / 512K / 1M. Luna is 0.208 / 0.173 / 0.050. Gemini is 0.474 / 0.473 / 0.205. Haiku, Nemotron, and Qwen all sit at 0.000. The Isaac lead over the second-best baseline grows from +0.133 at 256K to +0.295 at 1M — the longer the context, the bigger Isaac's edge. This isn't "fits 10M tokens" — it's "retrieves reliably inside 10M tokens."

Agent capability: four benchmarks, two first places

On BFCL v4 (function calling graded by AST and state-transition matching) Isaac scores 70.94, Luna 70.61, Haiku 67.52 — effectively a tie; the 0.33-point Isaac lead is parity, not a decisive margin. But the practical significance is: "you can have this on your own boundary at all."

τ³-bench (multi-turn customer service against an evolving simulated user): Isaac averages 0.662 across four domains, ranking first. Gemini is 0.631, Luna 0.527. On the banking sub-task the entire panel collapses — the best score in that column is 0.203, Isaac 0.186 — which is essentially a wash.

Terminal-Bench 2.1 (real shell, real test suite): Isaac 65.1% (56/86), Luna 69.8% (60/86). This is the one benchmark where a cloud baseline wins — and the gap is four tasks.

MCP-Atlas (discover and compose tools across 36 live MCP servers, neither server nor tool named): Isaac 74.59% in third place, behind Luna by 3.3 points, but using 9.10 turns per task versus Luna's 14.99. Lower coverage, materially better trajectory length.

Security: lowest ASR in same-installation comparison

DTAP red-teaming places the agent in simulated environments and measures whether injected attacks succeed. Isaac records the lowest scores on every axis: Direct ASR 36.0, Indirect ASR 35.2, Combined ASR 35.6, with 82.5 Benign Success Rate. Luna is 54.4 / 46.1 / 50.1. Gemini is 84.1 / 49.5 / 66.3. Two limits the report states plainly: indirect is "guards-inactive" because the harness matches native tool names while DTAP attacks arrive over MCP; and explicit refusals fired on only 1.5% of malicious tasks — most of the current safety is incidental rather than declined. Pokee writes this honestly.

Serving profile: 137k prefill on one B200

On a single NVIDIA B200 under the RULER workload: at 1M context, TTFT 23.6s, Prefill 42,400 tok/s, Decode 335 tok/s; at 10M context, TTFT grows to 72.9s, Prefill climbs to 137,200 tok/s, Decode holds flat near 335 — prefill scales with length, decode doesn't. Single-GPU workstation serves on RTX 4090 or RTX 5090. On Intel Arc Pro B70, prefill is 3.6–5× stock llama.cpp on the same card. On-device on Qualcomm Snapdragon X2 Elite and Intel Panther Lake NPU.

Pricing is $0.15 per million input tokens / $1.00 per million output, against 10M context. Luna is not sold commercially above 1M. Haiku, Nemotron, and Qwen all cap at 262K. "Lengths you can't buy from a cloud API" is the actual anchor.

Commentary: an agent deployment fork is opening

The last two years of agent stories have been a cloud race — stronger, longer, cheaper, all hosted. Pokee-Isaac takes the other branch: trade a moderate 28B parameter count for 10M context and agentic benchmark parity, and turn "data doesn't leave the boundary" from a compliance patch into a product feature.

The demand is real in regulated industries — healthcare, financial services, defense, legal, e-discovery. These are not customers who "prefer privacy" — they are customers whose data is not permitted to cross an external API boundary at all. When a 28B model can hit 93.3% on RULER at 10M, tie Luna on BFCL v4, rank first on agentic benchmarks, and record the lowest combined ASR on DTAP, then "on-prem" no longer requires a big capability concession. That is a fork.

Sources: Pokee-Isaac 28B model page | MarkTechPost coverage