Skip to content
Model Menu
Models
Compare
Leaderboard
Benchmarks
⌘K
Top
Chat
Coding
Agents
Writing
Vision
Image
Video
Speech
Embeddings
Decision
Music
Filters
Best for Vision & Documents
All models
2292
Chat & Knowledge
558
Coding
381
Agents & Tool Use
541
Writing & Language
360
Vision & Documents
395
Image Generation & Editing
183
Video Generation
148
Speech & Voice
358
Embeddings & Retrieval
671
Decision models
118
Music & Sound
29
MMMU-Pro
Chartography
OmniDocBench full v1.6
GDP.pdf · AA all-pass
Video-MME 2 · No subtitles
Arena Vision
Arena Document
All benchmarks
26
Vision & Documents benchmarks
26
×
All
26
Multimodal
12
Documents
3
Benchmark
By
Leader
Models
Multimodal
6
MMMU-Pro (vision)
College-level questions that require understanding images: charts, diagrams, photos
AA
Claude Opus 5.5
87.7%
124
Chartography
Expert chart reasoning over professional scientific, medical, financial and engineering charts
Surge
Gemini 4 Argon
71.6%
37
Arena Vision
Human pairwise preferences in the stated vision vote pool
Arena
Claude Fable 5
1,325
88
MMMU
validation
Image-grounded university-level questions across 30 disciplines; validation and test sets remain separate
MMMU
GPT-5.1
85.4%
41
OCRBench
v2 · CN
Tests visual text recognition, localization and reasoning; English and Chinese subsets remain separate
OCRBench
O
InternVL3 8B
53.5%
4
+1 versions & slices
v2 · EN
Tests visual text recognition, localization and reasoning; English and Chinese subsets remain separate
OCRBench
O
InternVL3 8B
49%
4
Documents
3
OmniDocBench
v1.6 · full
End-to-end document parsing, averaging text recognition, table structure and formula recognition under the stated full-set protocol
OmniDocBench
X
TeleOCR
96.9%
22
GDP.pdf
AA all-pass
Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes
Muse Wonder Full
32.6%
133
Arena Document
Human pairwise preferences in the stated document vote pool
Arena
Claude Opus 5
1,516
33
Reported by labs
11
CharXiv Reasoning
Reported by the lab with its own setup
Lab
Claude Opus 4.8
89.9
5
Chartography with tools
Reported by the lab with its own setup
Lab
Claude Opus 5
84
4
GDP.pdf AA
Reported by the lab with its own setup
Lab
Kimi K3
22
5
VideoMMMU
Reported by the lab with its own setup
Lab
Gemini 2.5 Pro
83.6
8
LVBench
Reported by the lab with its own setup
Lab
GPT-4o
48.9
2
BabyVision
Reported by the lab with its own setup
Lab
GPT-5.5
83.6
5
ChartQA Pro
Reported by the lab with its own setup
Lab
GPT-6 Astra
65.1
5
BabyVision with tools
Reported by the lab with its own setup
Lab
Claude Opus 5
94.1
4
ZeroBench-main with tools
Reported by the lab with its own setup
Lab
GPT-5.6 Sol
53
4
Dense200 bounding-box detection
Reported by the lab with its own setup
Lab
Mistral Large 4
42
4
BenchCAD w/ tools
Reported by the lab with its own setup
Lab
Kimi K3.1 Pro
92.7
1
Legacy · saturated or no longer reported
6
Video-MME
2 · without subtitles/audio
Grouped non-linear question scoring for video understanding; this is distinct from mean question accuracy
Video-MME
Gemini 3 Flash Preview
32.9%
16
+5 versions & slices
2 · with subtitles/audio
Grouped non-linear question scoring for video understanding; this is distinct from mean question accuracy
Video-MME
Gemini 3 Flash Preview
42.5%
16
1 · without subtitles/audio
Question accuracy across short, medium and long videos
Video-MME
r
Aria
67.6%
1
1 · with subtitles/audio
Question accuracy across short, medium and long videos
Video-MME
r
Aria
72.1%
1
2 · with subtitles/audio · 512 frames
Grouped non-linear question scoring for video understanding; this is distinct from mean question accuracy
Video-MME
Kimi K2.5
40.7%
1
2 · without subtitles/audio · 512 frames
Grouped non-linear question scoring for video understanding; this is distinct from mean question accuracy
Video-MME
Kimi K2.5
33%
1
No benchmark matches
Model
Arena Document
Per task
Price
Speed
Supports
Context
Claude Opus 5
Anthropic
1,516
high
$3.61
$5
/
$25
51
1M
Claude Fable 5.1
Anthropic
1,513
max
$7.63
$10
/
$50
69
1M
Claude Opus 4.6
Anthropic
1,507
high
—
$5
/
$25
45
1M
Claude Fable 5
Anthropic
1,496
unstated
—
$10
/
$50
—
1M
Claude Opus 4.7
Anthropic
1,495
unstated
—
$5
/
$25
—
1M
GPT-5.5
OpenAI
1,486
unstated
—
$5
/
$30
—
1.05M
GPT-5.6 Sol
OpenAI
1,483
xhigh
$1.18
$4
/
$20
85
1.05M
Claude Sonnet 4.6
Anthropic
1,482
unstated
—
$3
/
$15
—
1M
Claude Opus 4.8
Anthropic
1,475
high
—
$5
/
$25
—
1M
GPT-5.6 Terra
OpenAI
1,472
xhigh
$0.63
$2
/
$12
134
1.05M
GPT-5.4
OpenAI
1,471
unstated
—
$2.50
/
$15
—
1.05M
Muse Spark 1.3
Meta
1,471
max
$1.60
$1.25
/
$4.25
128
1M
GPT-6 Astra
OpenAI
1,468
max
$3.26
$10
/
$50
69
1.05M
Claude Sonnet 5
Anthropic
1,466
high
$1.79
$2
/
$10
71
1M
Muse Spark 1.1
Meta
1,465
unstated
—
$1.25
/
$4.25
—
1M
Claude Opus 4.5
Anthropic
1,462
unstated
—
$5
/
$25
—
200K
GPT-5.6 Luna
OpenAI
1,457
xhigh
$0.085
$0.20
/
$1.20
173
1.05M
Gemini 3.6 Flash
Google
1,456
high
$1.60
$0.75
/
$3.75
209
1M
Grok 4.6
xAI
1,452
high
$1.48
$2
/
$6
65
500K
Grok 4.5
xAI
1,452
unstated
—
$2
/
$6
—
500K
Kimi K2.6
Moonshot AI
Open
1,451
unstated
—
$0.95
/
$4
—
256K
Claude Sonnet 4.5
Anthropic
1,450
unstated
—
$3
/
$15
—
1M
Muse Spark
Meta
1,444
unstated
—
$1.25
/
$4.25
—
1M
Qwen3.7 Plus
Alibaba (Qwen)
1,444
unstated
—
$0.32
/
$1.28
—
1M
Gemini 3.1 Pro Preview
Google
1,444
unstated
—
$2
/
$12
—
1M
MiniMax M3
MiniMax
Open
1,435
unstated
—
$0.30
/
$1.20
—
524K
Gemma 4 31B
Google
Open
1,425
unstated
—
$0.10
/
$0.34
—
256K
Gemini 2.5 Pro
Google
1,421
unstated
—
$1.25
/
$10
—
1M
Claude Haiku 4.5
Anthropic
1,420
unstated
—
$1
/
$5
—
200K
GLM 5V Turbo
Z.ai
1,416
unstated
—
$1.20
/
$4
—
203K
Gemini 3 Flash Preview
Google
1,413
unstated
—
$0.50
/
$3
—
1M
GPT-5.2
OpenAI
1,405
high
—
$1.75
/
$14
—
400K
GPT-5.1
OpenAI
1,403
unstated
—
$1.25
/
$10
—
400K
Show 362 not measured on Arena Document