Coding models on Vertex AI, Bedrock and Foundry

LMArena WebDev ranking (overall), published 2026-10-28 · catalogs read 2026-10-29

Top 30

#ModelOrgRatingVertex AIBedrockFoundryOpenRouterIn $/MOut $/M
1Claude Opus 5.5 (Max)anthropic1810Yes · EUYes · EUYes · no EUYes$4.00$20.00
2GPT-6 Astra (Max)openai1773–Yes · no EUYes · EUYes$10.00$50.00
3Claude Sonnet 5.5 (xHigh)anthropic1770Yes · EUYes · EUYes · no EUYes$2.00$10.00
4Gemini 4 Carbon (High)google1768––––n/an/a
5GPT-6.1 Sol (Max)openai1751–Yes · no EUYes · EUYes$2.00$10.00
6Claude Fable 5.1 (Max)anthropic1746Yes · EUYes · no EUYes · no EUYes$10.00$50.00
7Muse Wonder Full (Max)meta1725––––n/an/a
8Claude Sonnet 5.5 (High)anthropic1711Yes · EUYes · EUYes · no EUYes$2.00$10.00
9Kimi K3.1 Pro (Max)moonshot1695–––Yes$2.00†$10.00†
10Claude Opus 5 (Max)anthropic1691Yes · EUYes · EUYes · no EUYes$5.00$25.00
11Gemini 4 Argon (High)google1679Yes · EU––Yes$2.00$10.00
12GPT-6 Sol (Max)openai1678–Yes · no EUYes · EUYes$2.00$10.00
13Qwen3.8-Max (0902)alibaba1676–––Yes$2.00†$6.00†
14GPT-6.1 Terra (Max)openai1673–Yes · no EUYes · EUYes$1.00$5.00
15Qwen3.8-Maxalibaba1672–––Yes$2.00†$6.00†
16DeepSeek-V4.1-Flash-20261017 (Max)deepseek1665Yes · no EU–Yes · no EUYes$0.30$1.20
17Claude Opus 5 (High)anthropic1658Yes · EUYes · EUYes · no EUYes$5.00$25.00
18Kimi K3 (Max)moonshot1656–Yes · no EU–Yes$3.00$15.00
19Muse Spark 1.3 (Max)meta1656Yes · no EU––Yes$1.25†$4.25†
20Muse Wonder (Max)meta1652–––Yes$4.00†$20.00†
21Grok 4.7 (xHigh)xai1637Yes · no EUYes · no EUYes · no EUYes$2.00$6.00
22MiMo-V2.6-Flashxiaomi1637–––Yes$0.14†$0.28†
23Hy4 previewtencent1631–––Yes$0.834†$2.501†
24Qwen3.8-Flash-Nextalibaba1628––––n/an/a
25MiMo-V2.6-Proxiaomi1625–––Yes$0.435†$0.87†
26Claude Fable 5 (High)anthropic1624Yes · EUYes · no EUYes · no EUYes$10.00$50.00
27GLM-5.3 (Max)zai1623–Yes · no EU–Yes$1.68$5.28
28Muse Spark 1.3 (xHigh)meta1620Yes · no EU––Yes$1.25†$4.25†
29DeepSeek-V4.1-Flash-20260910 (Max)deepseek1619Yes · no EU–Yes · no EUYes$0.30$1.20
30Grok 4.6 (High)xai1616Yes · no EUYes · no EUYes · no EUYes$2.00$6.00

Shortlist of cost-optimized frontier models

A model is on this list only if it meets all three filters:

EU residency
EU data residency and inference: the provider documents an EU-resident endpoint (EU, in What is what below). Global endpoints never count.
Cost
A base input price of $2.00 per 1M tokens or less.
Provided in the EU
By one of the three clouds, Vertex AI, Bedrock or Foundry. The EU endpoint and the price must come from the same one (Yes · EU in the table).
#ModelOrgRatingVertex AIBedrockFoundryOpenRouterIn $/MOut $/M
3Claude Sonnet 5.5 (xHigh)anthropic1770Yes · EUYes · EUYes · no EUYes$2.00$10.00
5GPT-6.1 Sol (Max)openai1751–Yes · no EUYes · EUYes$2.00$10.00
11Gemini 4 Argon (High)google1679Yes · EU––Yes$2.00$10.00

Open models in the top 30 for up to 256 GB at 8-bit and 4-bit

#ModelLicenseParamsPublished8-bit4-bit
24Qwen3.8-Flash-Nextqwen-community-1.0180BBF16 360 GB180 GB90 GB

What is what

In the tables

Yes
The provider lists the model in its public catalog, previews included. Quota and access to your account are not covered.
–
Not listed. A row that none of Vertex AI, Bedrock and Foundry lists is grey.
EU
An endpoint that keeps the data in the EU is documented. Global endpoints never count.
no EU
No EU endpoint is confirmed: none on the provider's region pages, the model is missing from them, or two sources disagree. Hover the label for the evidence.
Yes · EU
A green cell: the provider lists the model and documents an EU endpoint.
Tinted row
The base input price is $2.00 per 1M tokens or less, taking the lowest enterprise price. A † price never counts.
$/M
USD per 1M tokens at the base rate, the lowest enterprise price (from models.dev).
*
The enterprise providers charge different prices.
†
An OpenRouter price, shown only when no enterprise provider has one.
n/a
No price is known.

In the open-models table

Params
Total parameters from the Hugging Face page. A dash for packed weights, whose count cannot be read.
Published
Size of the weight files, with their format. Packed means compressed weights.
8-bit, 4-bit
The weights alone at that many bits per parameter, before any quantization overhead. A dash under 8-bit means it does not fit, or cannot be derived for packed weights; for those the 4-bit figure is the published size, an upper bound (≤).

Where it comes from

Vertex AI
Google Cloud. Its model docs and models.dev; EU from its endpoint locations.
Bedrock
Amazon Web Services. Its model cards and models.dev; EU from an eu.* inference profile, checked against the model card.
Foundry
Microsoft Azure. models.dev; EU from Microsoft's region tables, where Global Standard does not count.
OpenRouter
Personal use, global only. Its public API.
Open models
The leaderboard's license field says which are open. Sizes come from each model's Hugging Face page.

Changelog

2026-10-29 04:16 UTC
Gemini 4 Carbon (High): new at #4, rating 1768
GPT-5.6 Sol (xHigh, Codex Harness): left the top 30 (was #30, now #31)
2026-10-28 11:54 UTC
GPT-6.1 Terra (Max): new at #14. Bedrock Yes, no EU. Foundry Yes, EU. Vertex AI –. $1.00 in / $5.00 out
Gemini 4 Argon (High) enters the top 10 (#11 to #10, 1680); GPT-6 Sol (Max) leaves it (#10 to #11, 1677)
GLM-5.3-Flash leaves the top 30 (now #31) and the open-models table
Kimi K3 (Max): OpenRouter price now $0.2 in / $20 out