Kimi K3 vs Nova 2.0 Pro Preview: Release Comparison

Comparison of the Kimi K3 and Nova 2.0 Pro Preview releases: 2 and 3 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 5 models.

  • For intelligence, Kimi K3 scores highest: Kimi K3 (max) at 44, against Nova 2.0 Pro Preview (medium) at 14 for Nova 2.0 Pro Preview.
  • For output speed, Nova 2.0 Pro Preview is fastest: Nova 2.0 Pro Preview (low) at 113 t/s, against Kimi K3 (max) at 36 t/s for Kimi K3.

Releases compared

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3 incorporates 10 evaluations: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1
Estimate (independent evaluation forthcoming)

Intelligence Index vs. Cost per Intelligence Index Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task
Most attractive quadrant
Kimi K3
Pareto line

Cost

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better

Speed & Latency

Output Speed

Output tokens per second · Higher is better

Capability Scores

Capability Indices

Measures the performance of models on specific capabilities and industries
Finance & Accounting Index

Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

Strategy & Ops Index

Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

Legal Index

Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better

Healthcare & Medical Index

Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better

Engineering Index

Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2, AA-Briefcase, Terminal-Bench 4.0 · Higher is better

Economics Index

Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2, AA-Briefcase, AA-LCR v1.1 · Higher is better

Further details

Input modality
Output modality
Weights
Provider Benchmarks
Kimi K3 (max)
Kimi logoKimi
44
47
51
49
45
43
53
$2.00
$2.3
$3.00
$15.00
$0.30
$3,658
48k
32k
161M
36
4.63s
60.51s
74.48s
1228.11s
2.8T
104B active at inference time
1M
Jul 2026
-
Yes

Supports: text and image

Supports: text

ModalTogether AIDigitalOcean
+9
Kimi K3 (low)
Kimi logoKimi
30
33
40
35
-
30
37
$1.15
$2.3
$3.00
$15.00
$0.30
$1,190
12k
6k
22M
33
3.65s
63.64s
78.64s
338.72s
2.8T
104B active at inference time
1M
Jul 2026
-
Yes

Supports: text and image

Supports: text

KimiBasetenDatabricks
Nova 2.0 Pro Preview (medium)
Amazon logoAmazon
14
-
-
-
-
-
-
-
$1.5
$1.25
$10.00
$0.312
-
-
-
-
112
13.71s
31.56s
36.02s
-
-
256k
Nov 2025
-
Yes

Supports: text and image

Supports: text

Not available
-
Amazon Bedrock
Nova 2.0 Pro Preview (low)
Amazon logoAmazon
13
-
-
-
-
-
-
-
$2.1
$1.25
$10.00
-
-
-
-
-
113
9.19s
26.86s
31.28s
-
-
256k
Nov 2025
-
Yes

Supports: text and image

Supports: text

Not available
-
Amazon Bedrock
Nova 2.0 Pro Preview (Non-reasoning)
Amazon logoAmazon
10
-
-
-
-
-
-
-
$2.1
$1.25
$10.00
-
-
-
-
-
104
1.02s
1.02s
5.82s
-
-
256k
Nov 2025
-
No

Supports: text and image

Supports: text

Not available
-
Amazon Bedrock