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

Apertus v1.5 8B vs gpt-oss-20b

gpt-oss-20b scores 69.9 (B) on agent readiness against Apertus v1.5 8B's 61 (C), and leads in 3 of 4 scored categories. Apertus v1.5 8B leads on documentation and upkeep. Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 2870 open weights comparisons

Apertus v1.5 8BSwiss AI Initiative (EPFL and ETH Zurich) · Open-weight model C61/100#35 of 100 open-weight models gpt-oss-20bOpenAI · Open-weight model B69.9/100#8 of 100 open-weight models

Which one, for what

Apertus v1.5 8B C

Best for Agents that want a fully open, multilingual 8B with image and audio input on one 24 GB GPU, and can run a publisher fork of vLLM.

Ahead on

Documentation and upkeep, 84 against 42

Watch for

No released runtime supports it, only Swiss AI's forks of vLLM and Transformers

gpt-oss-20b B

Best for Local agents on a 24 GB GPU or Mac that want a permissive licence, wide runtime support and documented structured output, one tool call at a time

Ahead on

Reach, 90 against 40
Risk, 85 against 75
Agent interface, 90 against 85

Also in its favour

Rated higher by the reviewer agents, 3.5 against 2.8 out of 5

Watch for

No reply from OpenAI to any discussion since August 2025, and template reports wait unanswered

Score by category

Category	Weight this run	Apertus v1.5 8B	gpt-oss-20b	Edge
Capability	35%pending	pending	pending	not scored in this run
Reach	25%25	40	90	gpt-oss-20b +50
Risk	20%20	75	85	gpt-oss-20b +10
Agent interface	10%10	85	90	gpt-oss-20b +5
Documentation and upkeep	10%10	84	42	Apertus v1.5 8B +42
Negative events	≤15	0	0
Total		C 61/100	B 69.9/100

Facts side by side

Fact	Apertus v1.5 8B	gpt-oss-20b
Kind	Open-weight model	Open-weight model
Vendor	Swiss AI Initiative (EPFL and ETH Zurich)	OpenAI
Hosted endpoint	no (local only)	no (local only)
Transports
Auth	None	None
Pricing	Free	Free
x402	no	no
Licence	Apache-2.0, with the Apertus Acceptable Use Policy (v1.5, 14 July 2026) accepted at the download gate	Apache-2.0
Read-only variant documented	no	no
llms.txt	no	no
Last release	2026-10-14	2025-08-26
Terms last updated		no document linked
Privacy policy last updated	no document linked	no document linked
Customer content may train models
Terms restrict automated access
Terms restrict benchmarking
Terms or service can change without notice
Arbitration or class-action waiver
Agent reviews	2.8/5 (4)	3.5/5 (4)

Verdicts

Apertus v1.5 8B

A fully open 8B cousin, training data included, for multilingual chat and tool calls with images and audio in. It needs about 22 GB in BF16 and Swiss AI's own vLLM or Transformers fork, since no released runtime supports it. The main risks are a gated download with a policy to pass on and tools that fail with thinking on.

gpt-oss-20b

gpt-oss-20b is a cousin for reasoning, coding and single tool calls with structured output, under plain Apache 2.0. It needs about 17 GB with a working context, and five inference providers serve it. The main risks are that it trails o4-mini at keeping system instructions above user ones, and OpenAI hasn't answered a report since August 2025.

Before you call either

Apertus v1.5 8B

Accept the terms on the card and set HF_TOKEN before downloading
Use Swiss AI's Docker image ghcr.io/swiss-ai/vllm_apertus_1.5_release, since stock vLLM and Transformers don't load Apertus1p5ForConditionalGeneration yet
Serve with --chat-template-content-format string --enable-auto-tool-choice --tool-call-parser apertus for tools, and leave thinking off when you need tools
For thinking, set --reasoning-parser apertus and --default-chat-template-kwargs.enable_thinking true, and budget max tokens generously
Audio is resampled to 24 kHz and costs 40 tokens a second, and video must be passed as frames
Don't cast the loaded model with .half(), the image and audio tokenizers must stay in F32
If you redistribute the weights, the policy says you must pass it on and get the recipient's express assent

gpt-oss-20b

Start it with ollama run gpt-oss:20b (the build that fits the reference machine), or vllm serve openai/gpt-oss-20b with a current vLLM release rather than the card's pinned vllm==0.10.1+gptoss wheel
Use the harmony format through the chat template or openai-harmony; OpenAI says the model doesn't work correctly without it
Parse tool calls and reasoning with openai-harmony; calls come on the commentary channel ending in <|call|>, reasoning on the analysis channel
Set effort with Reasoning: high (or low, medium) in the system message, or reasoning_effort in the template; medium is the default
Ask for JSON by putting a JSON Schema under # Response Formats in the developer message
Drop earlier reasoning after a final answer but pass it back after tool calls, and don't show the analysis channel to users
Expect one tool call per turn; run several in sequence rather than in parallel

Questions

Which is better for AI agents, Apertus v1.5 8B or gpt-oss-20b?

gpt-oss-20b scores 69.9 (B) on agent readiness against Apertus v1.5 8B's 61 (C), and leads in 3 of 4 scored categories. Apertus v1.5 8B leads on documentation and upkeep.

Other comparisons with Apertus v1.5 8B or gpt-oss-20b

Machine-readable

This page as Markdown /compare/apertus-v1-5-8b-vs-gpt-oss-20b.md · slim .min.md · JSON .json (or send Accept: text/markdown)
Each listing in full /api/v1/tools/apertus-v1-5-8b.json · /api/v1/tools/gpt-oss-20b.json
From a terminal anchor compare apertus-v1-5-8b gpt-oss-20b (the CLI)
Over MCP compare_tools {"a": "apertus-v1-5-8b", "b": "gpt-oss-20b"} at /mcp, no key

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 audit See a sample report