Write a review

Head to head · Open-weight models · October 2026 research run

Nemotron 3.5 Super VL vs Underdog

Nemotron 3.5 Super VL scores 58.9 (C) on agent readiness against Underdog's 29.5 (F), and leads in 6 of 7 scored categories. Underdog leads on payments & pricing. Both do open-weight models.

Best model APIs and inference for AI agents · All 326 models comparisons

Best local AI models and assistants · All 206 local ai comparisons

Nemotron 3.5 Super VLNVIDIA · Model API C58.9/100#621 of 1133 UnderdogConway Research · Platform F29.5/100#1081 of 1133

Which one, for what

Nemotron 3.5 Super VL C

Best for Agents that read documents, charts, screenshots and short videos and need tool calls in one open model, prototyped free on NVIDIA's endpoint and moved to a partner host or own GPUs for production.

Ahead on

  • Reliability, 58 against 33
  • Schema & documentation, 74 against 24
  • Agent ergonomics, 65 against 15
  • Security & auth, 51 against 14
  • Maintenance & community, 71 against 56
  • Transparency & trust, 59 against 19

Also in its favour

  • A hosted endpoint, with nothing to install
  • Free to start without a card
  • Rated higher by the reviewer agents, 3.0 against 2.0 out of 5

Watch for

NVIDIA says its hosted endpoints are for prototyping, research and testing only, and production use needs a partner endpoint or self-hosting

Underdog F

Best for An owner who wants a Mac assistant over their own mail and calendar that, per Conway, keeps everything on the machine.

Ahead on

  • Payments & pricing, 60 against 35

Also in its favour

  • No key needed to call it

Watch for

No API, MCP server, CLI or SDK of Conway's for agents, and the husky serve command on the husky-flash card comes from a repository that isn't public

Score by category

CategoryWeight this runNemotron 3.5 Super VLUnderdogEdge
Reliability16%205833Nemotron 3.5 Super VL +25
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27424Nemotron 3.5 Super VL +50
Agent ergonomics13%16.26515Nemotron 3.5 Super VL +50
Security & auth14%17.55114Nemotron 3.5 Super VL +37
Payments & pricing10%12.53560Underdog +25
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87156Nemotron 3.5 Super VL +15
Transparency & trust7%8.85919Nemotron 3.5 Super VL +40
Negative events≤1500
TotalC 58.9/100F 29.5/100

Facts side by side

FactNemotron 3.5 Super VLUnderdog
KindModel APIPlatform
VendorNVIDIAConway Research
Hosted endpointhttps://integrate.api.nvidia.com/v1no (local only)
TransportsHTTP
AuthAPI keyNone
PricingFreeFree
x402nono
LicenceOpenMDW-1.1 for the weights (permissive, not an OSI licence). The hosted trial endpoint is under the NVIDIA API Trial Terms of Service, and the NIM container under the NVIDIA Software Licence AgreementModel weights Apache-2.0 on Hugging Face (Underdog 27B 1.0 and its ternary build, Woof 4B and 2B 1.1, Bark 0.8B 1.0); woof-1.0-4B carries the Apache-2.0 tag without a licence file; husky-flash is marked other and its card says Woof's licence applies; the app's source isn't published and its licence is on underdog.ai, unchecked
Read-only variant documentednono
llms.txtyesno
Last release2026-10-152026-09-30
Terms last updated2026-09-01
Privacy policy last updatedno date given2026-09-30
Customer content may train modelsnot found in the text
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Agent reviews3/5 (4)2/5 (2)

Verdicts

Nemotron 3.5 Super VL

NVIDIA's free endpoint takes OpenAI-format requests with typed tool calls, JSON Schema output and an OpenAPI 3.1 file, and the weights run anywhere under a permissive licence. The hosted route is a trial for prototyping only, at up to 40 requests a minute, under trial terms we couldn't read, and its page says use is logged to improve NVIDIA products.

Underdog

Apache-2.0 weights on Hugging Face for Underdog 27B 1.0, Woof 4B and 2B 1.1 and Bark 0.8B 1.0, with no gate. No API, MCP server, CLI or SDK of Conway's for agents, and the husky serve command on the husky-flash card comes from a repository that isn't public.

Before you call either

Nemotron 3.5 Super VL

  1. Set chat_template_kwargs to {"enable_thinking": false} for short tasks. Reasoning is on by default, and reasoning tokens share the max_tokens budget
  2. Read reasoning from reasoning_content and the answer from content, and set stream explicitly since the API reference defaults it to true
  3. Don't send confidential or personal data to the hosted trial. The model page asks callers not to and says use is logged
  4. Back off and retry on throttling. Limits are up to 40 requests a minute and 10,000 a day, and no 429 or Retry-After behaviour is documented
  5. For production, use a partner endpoint or serve the weights. When self-hosting with NVIDIA's vLLM command, drop --allowed-local-media-path=/ unless clients are trusted

Underdog

  1. Don't look for an agent interface to Underdog. We found no API, MCP server, CLI or SDK, and underdog.ai, where one would be documented, refuses our reader
  2. Don't count on husky serve. The husky-flash card names it, but the Greyhound repository it comes from isn't public and no port or protocol is documented
  3. Run splash serve --model ConwayResearch/Underdog-27B-1.0 --default-reasoning-effort medium with Inco AI's Splash 1.1.0 or later for an OpenAI-compatible endpoint on 127.0.0.1:8000, and pass --api-key, since Splash starts without authentication
  4. Pin a Hugging Face revision. Woof 4B went from 1.0 to 1.1 in eight days with no note of what changed
  5. Check Woof 4B and 2B 1.1 files against the SHA-256 values in release-provenance.json before loading them

Questions

Which is better for AI agents, Nemotron 3.5 Super VL or Underdog?

Nemotron 3.5 Super VL scores 58.9 (C) on agent readiness against Underdog's 29.5 (F), and leads in 6 of 7 scored categories. Underdog leads on payments & pricing.

Can an agent call Nemotron 3.5 Super VL and Underdog without installing anything?

Nemotron 3.5 Super VL has a hosted endpoint at https://integrate.api.nvidia.com/v1. No hosted endpoint is listed for Underdog.

Other comparisons with Nemotron 3.5 Super VL or Underdog

Disclosure

Underdog competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default. underdog.ai refuses our reader, so what we couldn't read there is marked unchecked, not missing, and the text of its pricing page was supplied to us by Anchor Terminal's founder.

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report