June 29, 2026 — 9:31 PM: Apodex posted on X that since shipping Apodex 1.0, its open 35B Apodex-1.0-mini has been outperforming models many times its size on FutureX — three #1 finishes in four weeks, with fresh scores of 59.17 (#1) and 58.42 (#2), ahead of Claude-Sonnet-4.6 (56.32), DeepSeek-V4-Pro (53.58), and GPT-5.5 (52.51).
Apodex calls itself a Self-Evolving Heavy-Duty Solver — built for questions whose answer isn't written down yet. That is future prediction, geopolitics, market moves, and open research problems where retrieval plus verification beats param count.
TL;DR — what people asked on X
| Question | Answer |
|---|---|
| What model is it? | Apodex-1.0-mini — 35B-A3B MoE, Qwen3.5 base, Apache 2.0 |
| Where to try? | apodex.ai — Deep Research mode uses Apodex-1.0-mini |
| FutureX scores? | #1 @ 59.17, #2 @ 58.42 (June 29 leaderboard) |
| Open weights? | Hugging Face — apodex/Apodex-1.0-mini |
| Why 35B beating Sonnet is wild? | Harness + verification-centric training — not raw logits alone |
| FIFA 2026 winner? | Apodex replied "checking our notes 👀" — the benchmark vibe in one reply |
What Apodex 1.0 actually ships
Apodex 1.0 is a verification-centric agent stack, not a single checkpoint drop:
| Component | Role |
|---|---|
| Apodex-1.0-mini | Open 35B-A3B weights — standard ReAct tool agent |
| Apodex-1.0-H | Heavy-duty mode — async agent team, shared evidence pool, global verifier |
| Apodex-1.0-0.8B / 2B / 4B SFT | Smaller open models trained on deep-research SFT data alone |
| AgentHarness | Open eval repo — reproduce BrowseComp, DeepSearchQA, HLE, etc. |
| AgentOS | Task-agnostic runtime for building and evaluating agent workflows |
| apodex.ai API | Product surface — Deep Research powered by mini |
Paper title: Apodex-1.0: A Verification-Centric Agent Team for Discoverative Intelligence (tech blog, Hugging Face model card).
Verification-first design
Most deep-research agents conflate finding and trusting. Apodex splits the loop:
- Orchestrator plans search and dispatches sub-agents
- Retrieval agents gather evidence in parallel
- Verifier audits the evidence graph before the answer ships
- Report pool logs findings, verdicts, and interventions — auditable, retractable, forkable
In heavy-duty deployment, Apodex claims coordination of up to 150 sub-agents over 15,000 steps on a single task — test-time scaling as architecture, not just more tokens.
That rhymes with Perplexity's agentic search thesis (search as code, evidence chains) and the agent memory systems debate — agents need data management, not just longer context.
FutureX — why the June 29 leaderboard matters
FutureX evaluates future prediction — forecasting outcomes before ground truth exists. That is deep research under uncertainty: track sources, detect regime change, synthesize conflicting signals, and commit to a calibrated answer.
Apodex submitted four experimental prediction harnesses built only on Apodex-1.0-mini. On the June 29 board they occupied #1 and #2 (and previously held top four per LinkedIn launch copy).
| Rank (Jun 29) | Score | Model / harness |
|---|---|---|
| #1 | 59.17 | Apodex harness (Apodex-1.0-mini) |
| #2 | 58.42 | Apodex harness (Apodex-1.0-mini) |
| — | 56.32 | Claude-Sonnet-4.6 |
| — | 53.58 | DeepSeek-V4-Pro |
| — | 52.51 | GPT-5.5 |
explainx.ai read: FutureX rewards evidence discipline, not memorization — the same axis where BrowseComp and DeepSearchQA live. A 35B open model leading here is a procurement signal for teams blocked from Fable/Mythos who still need frontier-grade research loops.
Deep-research benchmark table (standard ReAct)
From the Hugging Face model card — open checkpoints on the four-benchmark suite:
| Model | BrowseComp | BrowseComp-ZH | HLE-Text | DeepSearchQA |
|---|---|---|---|---|
| Apodex-1.0-mini | 71.5 | 80.6 | 46.8 | 82.2 |
| Apodex-1.0-4B-SFT | 48.8 | 63.5 | 32.9 | 69.9 |
| Apodex-1.0-2B-SFT | 27.9 | 35.0 | 18.2 | 49.9 |
| Apodex-1.0-0.8B-SFT | 13.9 | 10.7 | 11.2 | 25.8 |
Apodex-1.0-H (heavy agent team, not weights alone) pushes further — 90.3 BrowseComp, 94.4 DeepSearchQA, 60.8 HLE-text, 46.7 FrontierScience-Research, per the launch blog — edging GPT-5.5 on BrowseComp in Apodex's table and beating Claude Opus 4.8 and Kimi K2.6 on DeepSearchQA.
Data > params at small scale: Apodex-1.0-4B-SFT beats every open 30B-class model on BrowseComp and BrowseComp-ZH in their comparison — a direct challenge to "just scale parameters" thinking in the China free-models playbook.
Evaluations block benchmark-hosting websites during runs to reduce answer leakage from public repos — standard hygiene, worth noting when comparing vendor numbers.
Base model lineage — Qwen3.5-35B-A3B
Qwen/Qwen3.5-35B-A3B-Base → Qwen/Qwen3.5-35B-A3B → apodex/Apodex-1.0-mini
Post-training recipe (from model card):
- SFT on deep-research trajectories
- Agentic DPO
- RL on long agentic rollouts
Apodex claims additive gains — general knowledge (MMLU-Pro/Redux, C-Eval), math (AIME, HMMT), instruction-following (IFEval, IFBench), and long-context (LongBench v2) stay within ~1 point of matched Qwen3.5 bases. Coding is preserved too — Apodex-1.0-H reports 79.0 SWE-bench Verified and 58.4 Terminal-Bench v2 in the launch blog.
For local MoE coding trade-offs on the same Qwen family, see Qwen 3.6 27B dense vs 35B A3B — different fine-tune, same hardware class.
Apodex vs Agents-A1 — two 35B agent launches, same week
| Apodex-1.0-mini | Agents-A1 | |
|---|---|---|
| Ship date | Apodex 1.0 + FutureX post Jun 29 | ModelScope Jun 30 |
| Base | Qwen3.5-35B-A3B | qwen3_5_moe |
| Pitch | Verification-centric deep research | Heterogeneous long-horizon agent |
| BrowseComp | 71.5 (mini ReAct) | 75.51 (vendor table) |
| Standout | FutureX #1, DeepSearchQA 82.2 | GAIA 96, IFEval 94.8 SOTA |
| Open eval | AgentHarness | Agents-A1/evaluation |
| Product | apodex.ai Deep Research | ModelScope / HF weights |
Neither replaces Kimi K2.7-Code or LongCat-2.0 for repo-scale coding — pick by task axis.
How to run Apodex-1.0-mini
SGLang (recommended)
python3 -m sglang.launch_server \
--model-path apodex/Apodex-1.0-35B-A3B \
--tp 8 \
--host 0.0.0.0 \
--port 1234 \
--context-length 262144 \
--tool-call-parser qwen3_coder \
--reasoning-parser qwen3
vLLM
vllm serve apodex/Apodex-1.0-35B-A3B \
--tensor-parallel-size 8 \
--max-model-len 262144 \
--enable-auto-tool-choice \
--tool-call-parser qwen3_coder \
--reasoning-parser qwen3
Recommended sampling (agentic tasks)
| Parameter | Value |
|---|---|
temperature | 1.0 |
top_p | 0.95 |
repetition_penalty | 1.05 |
max_context_length | 262144 |
max_tokens | 32768 |
Apodex uses the Qwen3.5 chat template — tool calls as <function=...> blocks; pass schemas via OpenAI tools= parameter, not inlined in system prompt. Full Python agent loop is on the Hugging Face card.
Reproduce public benchmarks
git clone https://github.com/ApodexAI/AgentHarness
# Download benchmark pack from Hugging Face datasets/apodex/Deep-Research-Benchmarks
# See AgentHarness README for ReAct eval protocol
Supported suites include BrowseComp, BrowseComp-ZH, DeepSearchQA, HLE (text), FrontierScience, SuperChem, WideSearch — see AI benchmarks guide for how to read each.
Wire to harnesses
Point OpenAI-compatible endpoints at your server — same pattern as OpenCode local stack or Codex OSS. For MCP-heavy research, pair with Claude Code MCP patterns even if the model is Apodex-hosted.
Product — Deep Research at apodex.ai
X confirmed: Apodex-1.0-mini powers Deep Research mode on apodex.ai.
Use cases Apodex targets:
- Open-domain research where citations must survive audit
- Future prediction (FutureX-class questions)
- Scientific and professional QA with tool integration
- Mission-critical tasks where unsupported conclusions are unacceptable
That is a different buyer than "fast codegen" — closer to enterprise Fable alternatives research tiering: Apodex / DeepSeek / GLM API for volume + verify, closed frontier for edge cases if accessible.
Skepticism to keep
| Concern | Notes |
|---|---|
| Harness vs model | FutureX scores reflect prediction harness + mini, not bare chat completion |
| Heavy vs mini gap | 90.3 BrowseComp is Apodex-1.0-H team mode — not downloadable as one file |
| Benchmark leakage | Apodex blocks hosts; other labs may not — compare under AgentHarness when possible |
| Sonnet 4.6 naming | Verify exact API snapshot and harness parity on futurex.live |
| Self-evolving claim | Marketing term — read tech report for what actually updates (data, verifiers, policies) |
Bottom line
Apodex-1.0-mini is the strongest public signal yet that open 35B + verification architecture can beat closed Sonnet-, DeepSeek-, and GPT-class entries on future-facing research evals — not just static knowledge tests.
If you build research agents in 2026, run three checks:
- FutureX or BrowseComp on your tools with AgentHarness
- Deep Research mode on apodex.ai for qualitative audit trails
- Tiering against closed vs open alternatives and DeepSeek V4 pricing for cost
The 35B class is having a week: Apodex on FutureX (Jun 29), Agents-A1 on GAIA (Jun 30), Qwen 3.6 27B dense for local coding (Jun 29–30). Pick the axis you actually ship.
Related on explainx.ai
- Agents-A1 — InternScience 35B MoE (Jun 30) — same weight class, GAIA / long-horizon focus
- DeepSeek V4-Pro benchmarks and agent coding — FutureX competitor at 53.58
- GPT-5.5 / GPT-5.6 release guide — closed baseline at 52.51 on FutureX
- Perplexity search-as-code agentic search — BrowseComp-oriented product comparison
- Qwen 3.6 27B local dev — Qwen-family local coding path
- AI benchmarks complete guide — GAIA, BrowseComp, HLE, how to read tables
- Fable 5 open alternatives — enterprise research tiering
- Top Chinese AI companies 2026 — Qwen ecosystem context
Official: apodex.ai · Hugging Face — Apodex-1.0-mini · FutureX leaderboard · AgentHarness GitHub · Discord
FutureX scores and benchmark tables reflect Apodex's June 29, 2026 public posts and Hugging Face model card — leaderboard positions change daily. Verify live at futurex.live before citing ranks. Last updated: June 29, 2026.