# Apodex 1.1 and FrontierAgent: the harness, measured

> Satyajit Ghana — Head of Engineering @ Inkers Technology
> canonical: https://ai.thesatyajit.com/articles/apodex-frontier-agent
> date: 2026-08-25
> tags: agents, open-weights, benchmarks, harness, moe
Almost every agent release conflates two things. New weights land, they arrive wrapped in a new scaffold, and a single benchmark number reports the pair — which tells you the combination improved and nothing about which half did it. It is one of the more expensive ambiguities in the field, because the two halves have wildly different costs to reproduce.

[Apodex-1.1](https://huggingface.co/apodex/Apodex-1.1-mini) does something better, apparently without meaning to make a point of it. Their benchmark chart carries three rows per task: the previous model, the new model in a **single-agent ReAct loop**, and the new model in the **Agent Team** harness. Rows two and three are the same checkpoint. The gap between them is a measurement of a harness with the model held fixed, and it is bigger than I expected.

| | |
|---|---|
| Weights | `Apodex-1.1-mini` · **36B** total (`Qwen3.5-35B-A3B` fine-tune) · Apache 2.0 · FP8, NVFP4, GPTQ-Int4 variants |
| Context | **262,144** tokens deployed · SGLang or vLLM, `qwen3_coder` tool parser, `qwen3` reasoning parser |
| Harness | [ApodexAI/FrontierAgent](https://github.com/ApodexAI/FrontierAgent) — Apache 2.0, ReAct **and** Agent Team, TUI + eval runner |
| Flagship scores | APEX-Agents **38.5** · GDPval **78.8** · FrontierFinance **54.3** · FrontierScience-Research **63.3** · BioMysteryBench **35.3** · HLE **56.1** |
| Where it leads | **FrontierFinance** and **FrontierScience-Research** — the only two of six where it passes the best competing system |
| The harness premium | ≈**40%** of the 1.0 → 1.1 gain, averaged over six benchmarks · **+11.8** on BioMysteryBench alone |
| Report | [arXiv:2608.23283](https://arxiv.org/abs/2608.23283) · [tech blog](https://www.apodex.com/blog/apodex-1.1-scaling-agentic-intelligence-for-complex-work) |

<ModelCard repo="apodex/Apodex-1.1-mini" />

## The number nobody publishes

<HarnessDelta />

The green segment is the harness. Same weights above and below it; the only difference is whether the coordinator may decompose the request and dispatch bounded parallel assignments, or has to do the work in one long stateful loop.

Averaged over the six flagship benchmarks it is about 40% of everything gained from 1.0 to 1.1. On **BioMysteryBench** it is +11.8 against +5.9 for the model upgrade — the scaffolding contributes twice what the new weights do. On **GDPval** it is +9.3, against +10.2 for the model: near parity between a training run and a control-flow decision.

Two caveats before anyone over-reads that, and Apodex states the first themselves.

The first is that Agent Team is not free. It runs more sub-agents, which means more tokens and more wall-clock spend per task, and none of the charts report either. A harness that spends 4× the tokens to gain 10 points is a real result, but it is a different result from one that gains 10 points for free, and the published figures cannot distinguish them. This is the single biggest hole in the release.

The second is that these are Apodex's own evaluations of Apodex's own harness. They took an unusually good precaution — benchmark-hosting sites are blocked during evaluation, which addresses the most common way agentic scores get inflated — but the harness and the model were developed together, and the ReAct baseline is the one they chose to compare against rather than one an independent party picked.

Even discounted for both, the direction is the interesting part. **We are two or three years into a period where the scaffold is a first-class contributor to capability, and it is almost never measured separately.** Apodex measured it, arguably by accident, and the number is large.

<Figure
  src="/articles/apodex-frontier-agent/fig2.png"
  alt="A six-panel bar chart of Apodex-1.1 across APEX-Agents, GDPval, FrontierFinance, FrontierScience-Research, BioMysteryBench and Humanity's Last Exam. Each panel shows Apodex 1.1 Agent Team, Apodex 1.1 ReAct and Apodex 1.0 in blue at the top, with competing systems in grey beneath."
  caption="Apodex's published results. The three blue bars in each panel are the ladder; the grey bars are everyone else, and it is worth reading them as carefully as the blue ones. (Apodex, Apodex-1.1 model card.)"
/>

## Where the model actually places

Read the grey bars and the picture is more specific than "frontier-level performance across professional work, finance, scientific research, and general reasoning."

On **FrontierFinance** (54.3 vs Claude Fable 5 at 49.2) and **FrontierScience-Research** (63.3 vs DeepSeek V4 Flash at 55.0), Apodex-1.1 Agent Team leads. Those are the two Apodex names as wins, and they are wins.

On the other four it does not. GDPval 78.8 against Claude Opus 5's 89.4 is a ten-point gap. BioMysteryBench 35.3 against 49.4 is a fourteen-point gap. HLE 56.1 against 64.7. APEX-Agents 38.5 against 42.3.

That is a completely respectable position — an Apache-2.0 model that tops two research-heavy leaderboards and sits mid-pack against closed frontier systems on the rest. "Frontier-level" is doing some work in that sentence, but the underlying result does not need the adjective.

The `mini` checkpoint is the one you can actually run, and its story is the same shape at smaller scale. 36B total parameters on a `Qwen3.5-35B-A3B` base, so roughly 3B active per token — cheap to serve for what it does. FrontierFinance 50.2 leads the compared systems; APEX-Agent 27.7 is within 0.2 of Kimi K2.6's 27.9; FrontierScience-Research 51.7 trails DeepSeek V4 Flash's 55.0. And Agent Team beats ReAct on all three again: +3.5, +10.2, +6.7.

<Figure
  src="/articles/apodex-frontier-agent/fig3.png"
  alt="A three-panel bar chart for Apodex-1.1-mini across APEX-Agent, FrontierFinance and FrontierScience-Research, showing the Agent Team configuration above the ReAct configuration in blue, with competing systems in grey."
  caption="Apodex-1.1-mini. The harness premium reappears at 36B: +3.5, +10.2 and +6.7 from the same weights. (Apodex, Apodex-1.1 model card.)"
/>

## What the harness actually does

<Figure
  src="/articles/apodex-frontier-agent/fig1.png"
  alt="An architecture diagram. A query enters a main agent that creates sub-agents, assigns tasks, monitors progress, detects conflicts, triggers verification and synthesises a final report. An expert agent team of six specialists works in parallel with per-task status; their reports flow into a report pool and through a verification agent team of a conflict reviewer, fact checker and draft report reviewer before the final report."
  caption="The Agent Team workflow. The report pool on the left is the piece that makes the rest work: the coordinator's state is a board of task statuses and structured reports, never the sub-agents' raw observations. (ApodexAI/FrontierAgent.)"
/>

The mechanism behind the green segment is not exotic, and the diagram gives it away. The coordinator's state is a **task board** — pending, active, completed, blocked, cancelled — plus a pool of structured reports. It never holds the raw material the sub-agents worked through.

<ContextBudget />

That is the argument in one picture. A ReAct agent accumulates: every page it read, every command it ran, every error it recovered from remains in the same context for the rest of the task, so a long job spends its back half reasoning over a transcript mostly composed of things it already finished with. Past the window, something must be discarded, and the agent has no principled way to know which part it will need in an hour.

Fanning out does not reduce the work. It changes which agent has to hold it — and both the worst sub-agent context and the coordinator context stay roughly flat in total task size, as long as the width grows with the job.

Worth separating carefully: that control has two tabs and they are two different arguments. Widening `k` buys latency **and** buys context headroom, and only the second one plausibly explains a benchmark delta, since a benchmark does not score you on wall clock. If the Agent Team premium were mostly parallelism, it would show up as faster, not better. It shows up as better, which points at the context argument — or at the verification pass, which is the other thing the Team configuration adds and the ReAct one does not have.

That verification layer deserves its own line, because Apodex describes it as **Statement Review**: key claims are independently checked against their supporting sources, data and computations before delivery, and when evidence is insufficient or citations do not match, the system flags it, corrects the affected conclusion, and keeps the review inspectable. On research benchmarks specifically — which is where the premium is largest — a second pass that catches unsupported claims is exactly the intervention that would move a score. It is possible the harness premium is mostly this, and not the fan-out at all. The published numbers cannot separate them.

## The runtime you can actually use

FrontierAgent is Apache-2.0 and, unusually, is the same code that produced the benchmark numbers rather than a cleaned-up demo of it. The layering is deliberate:

```text
frontier_agent/  generic loop, scheduling, registries, AgentBus, observers
plugins/tools/   web, shell, file, sandbox, and team tool implementations
workflows/       ReAct and Agent Team pipelines, profiles, prompts, observers
apodex/          terminal CLI/TUI, approvals, sessions, traces, Docker path
benchmarks/      public harness plus bundled FrontierSearchBench/FrontierChallenge
```

The boundary that matters is between `workflows/` and everything else: the workflow engine that runs the TUI is the workflow engine that runs the evaluation, so a change in how the coordinator delegates shows up in both. A great many agent frameworks ship an eval harness that has quietly drifted from the product.

<SandboxTiers />

The filesystem contract is the part I would look at first in any agent runtime, and this one is right. Three roots — `/inputs` read-only, `/workspace` read-write, `/outputs` for persistent deliverables — shared by the **shell tool and the file tools alike**, so `rm -rf` obeys the same policy as a file write instead of escaping through a subprocess. That single detail separates a sandbox from a gesture at one.

The rest of the operational story is the unglamorous stuff that decides whether you can leave a thing running. Mutations show a diff and require approval unless `--yes`. Sessions are checkpointed, actions are traced locally, `/revert` restores changes, `--resume` continues a saved run. Typing while an agent runs queues an instruction that is injected at the next safe turn boundary rather than tearing down the active run — and in Agent Team mode it steers the coordinator while already-running sub-agents are allowed to finish, which is the correct semantics and slightly fiddly to implement. On macOS and Docker, `/outputs` maps to `.apodex/runs/<session-id>/outputs` on the host alongside the checkpoint, trace, engine log and trajectories.

Running it takes an OpenAI-compatible endpoint, Python 3.12, and `uv`:

```bash
git clone https://github.com/ApodexAI/FrontierAgent.git
cd FrontierAgent && uv sync --python 3.12 --extra dev
cp .env.example .env   # OPENAI_API_KEY / OPENAI_BASE_URL / OPENAI_MODEL

uv run frontier-agent --mode agent_team --cwd /path/to/project
```

Serving the weights yourself is a `Qwen3.5` deployment with two parsers attached:

```bash
vllm serve apodex/Apodex-1.1-mini --tensor-parallel-size 8 \
  --max-model-len 262144 --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder --reasoning-parser qwen3
```

One deployment note buried in the model card and easy to get wrong: pass tool schemas through the API's `tools=` parameter rather than inlining descriptions in the system prompt. The chat template renders them into the `<tool_call><function=…>` format the server-side parser expects, and hand-written descriptions in the prompt produce calls the parser cannot recover. The recommended sampling is `temperature 1.0`, `top_p 0.95`, `repetition_penalty 1.05`, `max_tokens 32768` — a notably high temperature, consistent with a model meant to explore a long trajectory rather than produce one right answer.

## The evaluation suite

Thirteen benchmarks ship with the runner: BrowseComp, xbench-DeepResearch, Humanity's Last Exam, SuperChem, FrontierScience-Research, FrontierScience-Olympiad, DeepSearchQA, WideSearch, FrontierSearchBench, OfficeQA, GDPval, APEX, OneMillion-Bench. It supports deterministic and model-based judges, resumable experiments, concurrent runs, progress inspection, and rerunning individual failures — which sounds like a list of features until you have tried to debug a hundred-task agentic eval where the only affordance is "run it all again."

```bash
uv run python -m benchmarks.public.runner.run_subprocess \
  --benchmark browsecomp --pipeline stateful-react-agent \
  --profile default --limit 1 --concurrency 1 --out ./results/smoke
```

The genuinely useful thing here is not that Apodex scores well on these. It is that the harness someone else's model needs in order to be compared fairly is now available, along with the evaluation code that produced the published numbers. If you want to know whether the ~40% harness premium reproduces on a model Apodex did not train, the apparatus to check is sitting in the repository.

## The ledger

**Real.** An Apache-2.0 36B-total / ~3B-active checkpoint that leads FrontierFinance and comes within 0.2 of the best APEX-Agent score, with FP8, NVFP4 and GPTQ-Int4 variants published alongside. An Apache-2.0 runtime that is the same code as the eval harness, with a shared shell/file sandbox, fail-closed authorization, checkpoints, traces and revert. Thirteen bundled benchmarks. And a three-row benchmark chart that isolates the harness — the most useful thing in the release and the thing least likely to be noticed.

**Unreported.** Token cost and wall clock for Agent Team versus ReAct, which is the number that decides whether a 40% harness premium is a bargain or a bill. No ablation separating fan-out from Statement Review, so the mechanism behind the premium is inferred rather than shown. No independent replication of the harness delta on a model Apodex did not train — though, to their credit, the code to do it is public.

**Overstated.** "Frontier-level performance" across all four listed domains, when the published charts show it trailing Claude Opus 5 by ten points on GDPval and fourteen on BioMysteryBench. Leading two of six is a good result stated accurately, and the accurate statement is right there in the same paragraph.

The thing I will keep from this release is not the model. It is the shape of the chart. Three rows, one checkpoint held fixed across two of them, and a number for the scaffold — published almost in passing, by a team who mostly seem to want you to look at the top bar.