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
All benchmarks
26
Vision & Documents benchmarks
26
×
All
26
Multimodal
12
Documents
3
Benchmark
By
Leader
Models
Multimodal
6
MMMU-Pro (vision)
MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos
AA
Claude Opus 5.5
87.7%
124
Chartography
Chartography: Expert chart reasoning over professional scientific, medical, financial and engineering charts
Surge
Gemini 4 Argon
71.6%
37
Arena Vision
Arena Vision · overall: Human pairwise preferences in the stated vision vote pool
Arena
Claude Fable 5
1,325
88
MMMU
validation
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
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
OCRBench 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
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
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
Arena Document · overall: 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
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
Video-MME 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
Video-MME 1 · without subtitles/audio: Question accuracy across short, medium and long videos
Video-MME
r
Aria
67.6%
1
1 · with subtitles/audio
Video-MME 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
Video-MME 2 · with subtitles/audio · with-subs; frames=512 · historical run: 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
Video-MME 2 · without subtitles/audio · no-subs; frames=512 · historical run: 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
Chartography
Per task
Price
Speed
Supports
Context
Gemini 4 Argon
Google
71.6
high
$1.99
$2
/
$10
84
1M
GPT-6 Astra
OpenAI
71
max
$3.26
$10
/
$50
69
1.05M
Claude Opus 5.5
Anthropic
66.3
max
$5.98
$4
/
$20
96
1M
GPT-6 Sol
OpenAI
53.6
max
$1.04
$2
/
$10
128
1.05M
Claude Fable 5.1
Anthropic
46.2
max
$7.63
$10
/
$50
69
1M
GPT-5.6 Sol
OpenAI
45
max
$1.99
$4
/
$20
114
1.05M
Gemini 3.8 Flash
Google
40.9
high
$1.24
$0.75
/
$3.75
149
1M
Claude Fable 5
Anthropic
34.8
max
$8.75
$10
/
$50
67
1M
Gemini 3.6 Flash
Google
34
medium
—
$0.75
/
$3.75
—
1M
GPT-5.6 Terra
OpenAI
34
max
$1.40
$2
/
$12
142
1.05M
Muse Spark 1.2
Meta
32.1
xhigh
$0.97
$1.25
/
$4.25
355
1M
GPT-5.6 Luna
OpenAI
31.4
max
$0.18
$0.20
/
$1.20
178
1.05M
GPT-5.5
OpenAI
31
xhigh
$2.63
$5
/
$30
113
1.05M
GPT-5.4
OpenAI
29.6
xhigh
—
$2.50
/
$15
127
1.05M
GPT-6 Luna
OpenAI
29.1
max
$0.068
$0.10
/
$0.50
138
1.05M
Muse Spark 1.3
Meta
27.6
xhigh
$1.37
$1.25
/
$4.25
273
1M
Claude Opus 5
Anthropic
27.3
max
$5.86
$5
/
$25
55
1M
Kimi K3
Moonshot AI
Open
26.6
max
$2.00
$3
/
$15
112
1M
Gemini 3.1 Pro
Google
26.1
high
—
$2
/
$12
—
1M
Muse Spark 1.1
Meta
24.4
xhigh
$1.38
$1.25
/
$4.25
280
1M
Grok 4.6
xAI
20.5
xhigh
$1.75
$2
/
$6
65
500K
Qwen3.8 Flash
Alibaba (Qwen)
Open
17.4
xhigh
—
$0.15
/
$0.47
—
262K
Muse Glimmer 30B
Meta
Open
17.2
xhigh
—
$0.30
/
$1.10
—
131K
Grok 4.5
xAI
17
high
$0.88
$2
/
$6
63
500K
Claude Sonnet 5
Anthropic
16.6
max
$5.09
$2
/
$10
80
1M
Claude Opus 4.7
Anthropic
16.5
max
—
$5
/
$25
63
1M
GLM 5.3 Flash
Z.ai
Open
16.3
max
$0.28
$0.15
/
$0.50
179
1M
Claude Opus 4.8
Anthropic
15.9
max
$4.08
$5
/
$25
66
1M
Qwen 3.5 Plus
Alibaba (Qwen)
15.9
thinking
—
$0.12
/
$0.69
—
1M
Qwen3.7 Plus
Alibaba (Qwen)
15.8
thinking
$0.22
$0.32
/
$1.28
58
1M
Grok 4.7
xAI
14.7
xhigh
$3.74
$2
/
$6
94
500K
Grok 4.3
xAI
12.9
high
$0.21
$1.25
/
$2.50
188
1M
Kimi K2.5
Moonshot AI
Open
12.6
thinking
—
$0.60
/
$3
78
256K
Kimi K2.6
Moonshot AI
Open
12.2
thinking
$0.80
$0.95
/
$4
109
256K
Gemini 3.5 Flash Lite
Google
10.2
minimal
—
$0.30
/
$2.50
—
1M
T
Inkling Small
Thinking Machines
Open
9.1
xhigh
—
$0.45
/
$1.20
—
256K
Mistral Large 3
Mistral
Open
9
unstated
—
$0.50
/
$1.50
—
262K
Show 358 not measured on Chartography