Sign in

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

EXAONE 4.5 33B vs LBS-27B

EXAONE 4.5 33B scores 61 (C) on agent readiness against LBS-27B's 55.8 (C), and leads in 3 of 4 scored categories. Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 6359 open weights comparisons

EXAONE 4.5 33BLG AI Research · Open-weight model C61/100#61 of 160 open-weight models LBS-27BinclusionAI (Ant Group) · Open-weight model C55.8/100#118 of 160 open-weight models

Which one, for what

EXAONE 4.5 33B C

Best for Researchers and students working on documents, Korean or multimodal agents who don't need commercial rights

Ahead on

  • Reach, 65 against 60
  • Agent interface, 85 against 70
  • Documentation and upkeep, 50 against 43

Watch for

Research and education only. No commercial use of the model or its output

LBS-27B C

Best for Agents with about 96 GB of GPU memory that need to find click targets on dense professional screenshots, or read fine detail in large images, and can run a small crop loop and wait for independent results.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

No independent benchmark result yet; ScreenSpot-Pro, OS-World-G, PerceptionBench and HR-Bench numbers are inclusionAI's own runs

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Agent interface EXAONE 4.5 33B +15

EXAONE 4.5 33B 85

Chat template 20, chat_template.jinja in the repository (5,930 characters). Tool-calling format 25, the card's vLLM command names the parser, hermes with auto tool choice, and its agentic example calls tools from MCP servers through the OpenAI-compatible API, so declaration and return follow that API. Trained tool calling 20, the card reports agentic tool use among its language results and shows an agent run with several tool servers, and the template renders every call in a turn. Structured output 0, Nothing on the card about JSON or schema-constrained output. Reasoning control 10, enable_thinking is on by default and the card says to set it false for the non-reasoning mode, with an example of each. Context 10, 262,144 tokens per the card's configuration table and config.json, and the card's serve commands run at that length. 20 + 25 + 20 + 0 + 10 + 10 = 85.

LBS-27B 70

The chat template earns 20, Qwen's Jinja file in the repository. The tool-calling format earns 10, as general tool calls rest on the inherited template and the crop action is parsed by inclusionAI's own code, not a runtime parser. Trained tool calling earns 20 for up to two crop actions per turn learned in GRPO. Structured output earns 0. Reasoning control earns 10, with reasoning effort documented and the reasoning shown as think text. Context earns 10 for 262,144 tokens with no scaling.

Documentation and upkeep EXAONE 4.5 33B +7

EXAONE 4.5 33B 50

Model card 20, Uses (the quickstart's question answering, document and agent examples), limitations, the architecture, the parameters, the context, the languages (in the metadata) and a knowledge cut-off of December 2024 are all on the card. Training data 5, A knowledge cut-off and one line on excluding personal, harmful and biased content, with no sources or sizes. Last change 10, the main repository last changed on 6 July 2026 (dependencies moved to official releases), 127 days before this check, and the FP8 repository on 9 August, 93 days. Responsiveness 0, none of the 5 most recent discussions that aren't pull requests (13 April to 4 May 2026) has a reply from an LGAI-EXAONE member, counted on 10 November by author flags and dates with a script, text not read. Version policy 5, EXAONE 4.0 and 4.0.1 stay in their own repositories and 4.5 came out in new ones, with no dated note on the older cards that we read. File health 10, Config, template and card agree on the architecture and the 262,144 tokens, and a July commit moved the dependencies to released versions. 20 + 5 + 10 + 0 + 5 + 10 = 50.

LBS-27B 43

The model card earns 8, with intended use, one limitation and parameters, and no architecture, context, languages or cut-off. Training data earns 5 for a general description of synthetic GUI data with no cut-off. Last change earns 20 for 26 October 2026. Responsiveness earns 0, the one discussion unanswered. Version policy earns 5 for a first release. File health earns 5, as the config still sets an MTP layer the weights lack and the card names a reasoning setting the template refuses.

Reach EXAONE 4.5 33B +5

EXAONE 4.5 33B 65

Memory 20, the smallest build at 4 bits is LG's IQ4_XS GGUF, 18.03 GB with the 2.57 GB projector, and 20.60 GB × 1.2 = 24.7 GB, within 32 GB. Without the projector, for text only, it would fit 24 GB. Runtimes 15, Released vLLM 0.33.0 has exaone4_5.py, Transformers 5.22.2 has the exaone4_5 model, and llama.cpp b12242 has the architecture, with LG's own GGUF. Three at 5 each. Builds 15, LG publishes GGUF at five quantised precisions, an AWQ build and an FP8 build. Terms 5, Research and educational use only. Download 10, the Hub API reports gated false for all four repositories on 10 November 2026, so the files download with no account and no click-through, though the licence says downloading is acceptance. Hosted 0, Hugging Face maps no inference provider to it, and the card names no API that serves it. 20 + 15 + 15 + 5 + 10 + 0 = 65.

LBS-27B 60

Memory earns 10, since the only build is 54.73 GB of BF16, about 66 GB with a fifth added, which fits the reference machine but not 64 GB. Runtimes earn 25 from released vLLM, SGLang, Transformers and llama.cpp, which all carry Qwen3.8-27B's architecture, and Ollama through the llama.cpp release it pins, so 25. Builds earn 0, as inclusionAI publishes no quantised build and the GGUF copies are bartowski's and mradermacher's. Terms earn 15 for Apache 2.0 with nothing added, on the weights and on the base. Download earns 10, with no gate. Hosted earns 0, as no provider or inclusionAI API serves it.

Score by category

CategoryWeight this runEXAONE 4.5 33BLBS-27BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%256560EXAONE 4.5 33B +5
Risk20%205050even
Agent interface10%108570EXAONE 4.5 33B +15
Documentation and upkeep10%105043EXAONE 4.5 33B +7
Negative events≤1500
TotalC 61/100C 55.8/100

Facts side by side

FactEXAONE 4.5 33BLBS-27B
KindOpen-weight modelOpen-weight model
VendorLG AI ResearchinclusionAI (Ant Group)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceEXAONE AI Model License Agreement 1.2 - NC (research and education only)Apache-2.0 (the card's metadata and licence section; the LICENSE file sits in the GitHub repository inclusionAI/UI-Venus on its LBS branch, not in the Hugging Face repository)
Read-only variant documentednono
llms.txtnono
Last release2026-07-062026-10-26
Terms last updatednot read yetno document linked
Privacy policy last updatedno document linkedno document linked

How the scores have moved

EXAONE 4.5 33B

No score change since it was listed.

LBS-27B

Verdicts

EXAONE 4.5 33B

A well-documented vision-language model with a full set of builds, tool calling, switchable reasoning, a 256K context and a stated knowledge cut-off. The licence decides whether you can use it: research and education only, output included, and LG can change the terms. Nothing answered on the repository and no safety results.

LBS-27B

A 27B Qwen3.8 fine-tune for GUI grounding that zooms into screenshots over a few turns before naming a point, and inclusionAI says it also helps with fine detail in large images. It needs about 96 GB at BF16 and a client that runs its crop actions. Every result so far is inclusionAI's own, with no safety results or injection guidance.

Before you call either

EXAONE 4.5 33B

  1. Don't use it, or anything it writes, commercially. The licence covers the output too
  2. Serve it with vLLM and --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser hermes
  3. Set enable_thinking false for a direct answer. Thinking is on by default
  4. Use temperature 1.0, top_p 0.95 and presence_penalty 1.5 in general, and temperature 0.6 with top_k 20 for documents and Korean
  5. For llama.cpp, load a projector file from LG's GGUF repository with the weights for image input
  6. Its knowledge stops at December 2024

LBS-27B

  1. Serve with vllm serve inclusionAI/LBS-27B --tensor-parallel-size 4 --max-model-len 65536, which is what the card's wrapper script runs; keep the context at 32,768 or more for multi-turn images
  2. Build the system prompt with build_system_prompt from the LBS branch's zoomin_grounding_protocol.py, send the screenshot after image_path: <name>, and don't pass tools; the model answers in plain text
  3. Parse <action>crop_image(image_path=..., x1=..., y1=..., x2=..., y2=...)</action>, cut the crop yourself and return it with its mapping to the original image; allow at most two crops per turn and three per episode
  4. Read the final answer as [x.xx,y.yy] on a 0 to 1000 scale of the original image, and use your own executor to click
  5. Pass reasoning_effort as xhigh, medium or low only, since the template raises an error for high, and don't count on thinking_budget, which the template ignores
  6. Don't turn on MTP speculative decoding; the MTP weights aren't in the repository though config.json names one MTP layer

Questions

Which is better for AI agents, EXAONE 4.5 33B or LBS-27B?

EXAONE 4.5 33B scores 61 (C) on agent readiness against LBS-27B's 55.8 (C), and leads in 3 of 4 scored categories.

Other comparisons with EXAONE 4.5 33B or LBS-27B

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