Benchmark suiteLatest source data: Oct 16, 2026Checked: October 18, 2026

Long context rankings.

A focused page for document-heavy and retrieval-heavy work. The current view uses Docs, Search, and Text Arena signals while HELM Long Context and context-window metadata are prepared as the next data layer.

Ranked models

135

Docs, search, or text signal

Docs coverage

44

Document Arena rows

Search coverage

42

Search Arena rows

HELM context

Planned

Long-context leaderboard feed

Context formula

Document skill first, retrieval support second.

The context proxy blends Document Arena, Search Arena, and Text Arena scores. It does not claim a context-window size or true long-context pass rate until a dedicated source row is available.

Long-context proxy

Higher proxy index is better. HELM Long Context is shown as a planned source rather than a hidden assumption.

Top 30 of 135

#1
Gemini 4 Argon

Gemini 4 Argon (High)

GoogleProprietary
100context proxy
Docs
Not listedDocs Arena
Search
Not listedSearch Arena
Text
1,524Text Arena rank #1
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#2
Claude Opus 4.6 High

claude-opus-4-6-high

AnthropicProprietary
96context proxy
Docs
1,495Docs Arena rank #2
Search
Not listedSearch Arena
Text
Not listedText Arena
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#3
Claude Opus 4.6

claude-opus-4-6

AnthropicProprietary
95context proxy
Docs
1,494Docs Arena rank #4
Search
Not listedSearch Arena
Text
Not listedText Arena
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#4
Claude Opus 4.7 High

claude-opus-4-7-high

AnthropicProprietary
94context proxy
Docs
1,493Docs Arena rank #5
Search
Not listedSearch Arena
Text
Not listedText Arena
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#5
Claude Fable 5.1 Max

claude-fable-5.1-max

AnthropicProprietary
94context proxy
Docs
1,493Docs Arena rank #6
Search
Not listedSearch Arena
Text
Not listedText Arena
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#6
Claude Fable 5

Claude Fable 5 (High)

AnthropicProprietary
92context proxy
Docs
1,499Docs Arena rank #1
Search
Not listedSearch Arena
Text
1,504Text Arena rank #4
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#7
Claude Opus 4.7

claude-opus-4-7

AnthropicProprietary
88context proxy
Docs
1,494Docs Arena rank #3
Search
1,210Search Arena rank #12
Text
Not listedText Arena
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#8
Claude Fable 5.1 High

claude-fable-5.1-high

AnthropicProprietary
87context proxy
Docs
Not listedDocs Arena
Search
1,233Search Arena rank #4
Text
Not listedText Arena
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#9
Claude Opus 5 High

claude-opus-5-high

AnthropicProprietary
86context proxy
Docs
1,490Docs Arena rank #7
Search
1,214Search Arena rank #10
Text
Not listedText Arena
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#10
Claude Fable 5 High

claude-fable-5-high

AnthropicProprietary
85context proxy
Docs
Not listedDocs Arena
Search
1,229Search Arena rank #6
Text
Not listedText Arena
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#11
GPT-5.6 Sol xHigh

gpt-5.6-sol-xhigh

OpenAIProprietary
84context proxy
Docs
1,489Docs Arena rank #8
Search
1,258Search Arena rank #1
Text
1,485Text Arena rank #21
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#12
GPT-5.5 Search

gpt-5.5-search

OpenAIProprietary
84context proxy
Docs
Not listedDocs Arena
Search
1,226Search Arena rank #8
Text
Not listedText Arena
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#13
Muse Wonder

Muse Wonder (Max)

MetaProprietary
83context proxy
Docs
Not listedDocs Arena
Search
Not listedSearch Arena
Text
1,509Text Arena rank #2
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#14
Claude Opus 4.6 Search

claude-opus-4-6-search

AnthropicProprietary
82context proxy
Docs
Not listedDocs Arena
Search
1,222Search Arena rank #9
Text
Not listedText Arena
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#15
Claude Opus 5.5

Claude Opus 5.5 (High)

AnthropicProprietary
81context proxy
Docs
Not listedDocs Arena
Search
Not listedSearch Arena
Text
1,508Text Arena rank #3
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#16
GPT-6.1 Sol Max

gpt-6.1-sol-max

OpenAIProprietary
76context proxy
Docs
Not listedDocs Arena
Search
1,250Search Arena rank #2
Text
1,484Text Arena rank #22
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#17
Claude Opus 5.5 Medium

claude-opus-5.5-medium

AnthropicProprietary
76context proxy
Docs
Not listedDocs Arena
Search
1,211Search Arena rank #11
Text
Not listedText Arena
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#18
Claude Opus 4.8 High

claude-opus-4-8-high

AnthropicProprietary
75context proxy
Docs
1,486Docs Arena rank #9
Search
Not listedSearch Arena
Text
1,481Text Arena rank #25
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#19
Claude Fable 5.1

Claude Fable 5.1 (Max)

AnthropicProprietary
74context proxy
Docs
Not listedDocs Arena
Search
Not listedSearch Arena
Text
1,502Text Arena rank #6
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#20
Gemini 3.1 Pro Grounding

gemini-3.1-pro-grounding

GoogleProprietary
74context proxy
Docs
Not listedDocs Arena
Search
1,207Search Arena rank #14
Text
Not listedText Arena
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#21
Muse Spark 1.1

Muse Spark 1.1

MetaProprietary
73context proxy
Docs
1,479Docs Arena rank #12
Search
Not listedSearch Arena
Text
1,490Text Arena rank #13
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#22
GPT-6 Astra Max

gpt-6-astra-max

OpenAIProprietary
73context proxy
Docs
1,473Docs Arena rank #17
Search
1,246Search Arena rank #3
Text
1,477Text Arena rank #30
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#23
Claude Sonnet 4.6 Search

claude-sonnet-4-6-search

AnthropicProprietary
71context proxy
Docs
Not listedDocs Arena
Search
1,202Search Arena rank #17
Text
Not listedText Arena
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#24
GPT-5.5

gpt-5.5

OpenAIProprietary
71context proxy
Docs
1,483Docs Arena rank #10
Search
Not listedSearch Arena
Text
1,477Text Arena rank #31
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#25
Gemini 3 Pro Grounding

gemini-3-pro-grounding

GoogleProprietary
71context proxy
Docs
Not listedDocs Arena
Search
1,201Search Arena rank #18
Text
Not listedText Arena
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#26
GPT-5.5 High

gpt-5.5-high

OpenAIProprietary
71context proxy
Docs
1,480Docs Arena rank #11
Search
Not listedSearch Arena
Text
1,481Text Arena rank #26
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#27
Qwen3.8 Max

qwen3.8-max

AlibabaProprietary
69context proxy
Docs
Not listedDocs Arena
Search
1,229Search Arena rank #5
Text
1,482Text Arena rank #24
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#28
Muse Spark 1.3 Max

muse-spark-1.3-max

MetaProprietary
69context proxy
Docs
1,468Docs Arena rank #19
Search
Not listedSearch Arena
Text
Not listedText Arena
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#29
Claude Opus 4.6

Claude Opus 4.6

AnthropicProprietary
69context proxy
Docs
Not listedDocs Arena
Search
Not listedSearch Arena
Text
1,497Text Arena rank #8
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena
#30
GPT-5.4 Search

gpt-5.4-search

OpenAIProprietary
68context proxy
Docs
Not listedDocs Arena
Search
1,196Search Arena rank #20
Text
Not listedText Arena
Context
HELM pendinglong-context feed
Docs ArenaSearch ArenaText Arena

Benchmark guide

What the scores mean.

A quick reading key for long-context rankings, document-heavy work, retrieval signals, and planned context-window data.

Higher: context proxyHELM feed planned
What does the long-context proxy measure?

The long-context proxy blends Document Arena, Search Arena, and Text Arena scores. It is meant to surface models that appear strong on document-heavy and retrieval-heavy work while dedicated long-context benchmarks are being wired.

Does this measure context window size?

Not yet. Context window size and max output tokens need a reliable source before they become table fields. This ranking focuses on public task performance, not advertised token limits.

Why is HELM Long Context listed as planned?

HELM Long Context is the right benchmark family for more direct long-context evaluation, but it is not mixed into the score until the feed is integrated and matched cleanly to model rows.

How should I read document and search scores?

Document scores point toward long-form reading and file-style tasks. Search scores point toward retrieval-style workflows. Both are useful signals, but neither proves that a model can reliably use every token in a huge context window.