AI Model Picker
Models
Compare
Suggestions
About
API
Model Suggestions
Updated
10/1/26, 2:45 PM UTC
·
Artificial Analysis
Best for General Use (Balanced)
Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)
New
Anthropic
·
9/28/26
Score: 58.5
Pricing (per 1M)
Input:
$2.00
Output:
$10.00
Speed
Output t/s:
145.2
TTFT:
265.20s
Benchmarks
Intelligence
:
56
HLE
:
55.0
SCICODE
:
61.0
LCR
:
82.7
TERMINALBENCH V4 0
:
63.6
+ Compare
Copy ID
Muse Spark 1.3 (Max)
Meta
·
9/2/26
Score: 58.3
Pricing (per 1M)
Input:
$1.25
Output:
$4.25
Speed
Output t/s:
172.2
TTFT:
35.11s
Benchmarks
Intelligence
:
48.1
Coding
:
75.8
GPQA
:
93.5
HLE
:
48.7
SCICODE
:
58.8
LCR
:
83.0
TERMINALBENCH V2 1
:
84.3
TERMINALBENCH V4 0
:
33.3
TAU BANKING
:
50.5
+ Compare
Copy ID
Muse Spark 1.3 (Xhigh)
Meta
·
9/2/26
Score: 57.6
Pricing (per 1M)
Input:
$1.25
Output:
$4.25
Speed
Output t/s:
216.6
TTFT:
30.77s
Benchmarks
Intelligence
:
45.1
Coding
:
76.5
GPQA
:
94.1
HLE
:
47.5
SCICODE
:
59.7
LCR
:
83.0
TERMINALBENCH V2 1
:
85.4
TERMINALBENCH V4 0
:
16.7
TAU BANKING
:
47.2
+ Compare
Copy ID
#4
DeepSeek V4.1 Flash (Max)
DeepSeek
Score: 56.6
#5
Gemini 3.8 Flash (High)
Google
Score: 55.6
#6
Gemini 3.8 Flash (Medium)
Google
Score: 54.9
Best for Coding Tools
Gemini 3.8 Flash (High)
Google
·
9/2/26
Score: 77.9
Pricing (per 1M)
Input:
$0.75
Output:
$3.75
Speed
Output t/s:
237.7
TTFT:
13.38s
Benchmarks
Intelligence
:
40.9
Coding
:
76.3
GPQA
:
95.3
HLE
:
47.8
SCICODE
:
56.6
LCR
:
81.3
TERMINALBENCH V2 1
:
87.6
TERMINALBENCH V4 0
:
19.7
TAU BANKING
:
44.9
+ Compare
Copy ID
Muse Spark 1.3 (Xhigh)
Meta
·
9/2/26
Score: 77.9
Pricing (per 1M)
Input:
$1.25
Output:
$4.25
Speed
Output t/s:
216.6
TTFT:
30.77s
Benchmarks
Intelligence
:
45.1
Coding
:
76.5
GPQA
:
94.1
HLE
:
47.5
SCICODE
:
59.7
LCR
:
83.0
TERMINALBENCH V2 1
:
85.4
TERMINALBENCH V4 0
:
16.7
TAU BANKING
:
47.2
+ Compare
Copy ID
Muse Spark 1.3 (Max)
Meta
·
9/2/26
Score: 76.5
Pricing (per 1M)
Input:
$1.25
Output:
$4.25
Speed
Output t/s:
172.2
TTFT:
35.11s
Benchmarks
Intelligence
:
48.1
Coding
:
75.8
GPQA
:
93.5
HLE
:
48.7
SCICODE
:
58.8
LCR
:
83.0
TERMINALBENCH V2 1
:
84.3
TERMINALBENCH V4 0
:
33.3
TAU BANKING
:
50.5
+ Compare
Copy ID
#4
Gemini 3.8 Flash (Medium)
Google
Score: 75.9
#5
Gemini 3.8 Flash (Low)
Google
Score: 75.4
#6
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
Anthropic
Score: 75.2
Best Value (Cost Efficient)
MiMo-V2.6-Pro
Xiaomi
·
9/21/26
Score: 62.1
Pricing (per 1M)
Input:
$0.43
Output:
$0.87
Speed
Output t/s:
49.2
TTFT:
3.42s
Benchmarks
Intelligence
:
46.3
HLE
:
49.4
SCICODE
:
60.9
LCR
:
86.3
TERMINALBENCH V4 0
:
34.8
+ Compare
Copy ID
DeepSeek V4.1 Flash (Max)
DeepSeek
·
9/10/26
Score: 61.9
Pricing (per 1M)
Input:
$0.30
Output:
$1.20
Speed
Output t/s:
226.7
TTFT:
0.84s
Benchmarks
Intelligence
:
39.5
HLE
:
39.2
SCICODE
:
51.9
LCR
:
84.0
TERMINALBENCH V4 0
:
26.8
+ Compare
Copy ID
Muse Spark 1.3 (Max)
Meta
·
9/2/26
Score: 61.2
Pricing (per 1M)
Input:
$1.25
Output:
$4.25
Speed
Output t/s:
172.2
TTFT:
35.11s
Benchmarks
Intelligence
:
48.1
Coding
:
75.8
GPQA
:
93.5
HLE
:
48.7
SCICODE
:
58.8
LCR
:
83.0
TERMINALBENCH V2 1
:
84.3
TERMINALBENCH V4 0
:
33.3
TAU BANKING
:
50.5
+ Compare
Copy ID
#4
GPT-6 Luna (Max)
OpenAI
Score: 60.5
#5
GLM 5.3 Flash
Z AI
Score: 60.5
#6
Muse Spark 1.3 (Xhigh)
Meta
Score: 60.1
Smart & Fast (Intel > Speed > Price)
Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)
New
Anthropic
·
9/28/26
Score: 57.9
Pricing (per 1M)
Input:
$2.00
Output:
$10.00
Speed
Output t/s:
145.2
TTFT:
265.20s
Benchmarks
Intelligence
:
56
HLE
:
55.0
SCICODE
:
61.0
LCR
:
82.7
TERMINALBENCH V4 0
:
63.6
+ Compare
Copy ID
Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)
Anthropic
·
9/22/26
Score: 54.8
Pricing (per 1M)
Input:
$4.00
Output:
$20.00
Speed
Output t/s:
96.0
TTFT:
481.19s
Benchmarks
Intelligence
:
57.6
HLE
:
61.4
SCICODE
:
66.9
LCR
:
84.7
TERMINALBENCH V4 0
:
59.6
+ Compare
Copy ID
Muse Spark 1.3 (Max)
Meta
·
9/2/26
Score: 53.5
Pricing (per 1M)
Input:
$1.25
Output:
$4.25
Speed
Output t/s:
172.2
TTFT:
35.11s
Benchmarks
Intelligence
:
48.1
Coding
:
75.8
GPQA
:
93.5
HLE
:
48.7
SCICODE
:
58.8
LCR
:
83.0
TERMINALBENCH V2 1
:
84.3
TERMINALBENCH V4 0
:
33.3
TAU BANKING
:
50.5
+ Compare
Copy ID
#4
Claude Sonnet 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback)
Anthropic
Score: 52.7
#5
Claude Opus 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback)
Anthropic
Score: 52.6
#6
Muse Spark 1.3 (Xhigh)
Meta
Score: 52.3