Navigate
Advertise here

Gemini 4 Argon (low) vs Kimi K3 (max)

Kimi K3 (max) leads on average score with 8.3 vs 8.2. Gemini 4 Argon (low) has the lower benchmark cost at $0.438 vs $3.409. Gemini 4 Argon (low) is faster at 5.72s vs 139.41s, with pass rates of 79.7% vs 78.3%.

Last updated at: 2026-10-13

Compared models

Rank
#92
Total Output Tokens
6,097
Response Time (avg)
5.72s
Total Cost
$0.438
Rank
#87
Total Output Tokens
233,327
Response Time (avg)
139.41s
Total Cost
$3.409
Recommended model Gemini 4 Argon (low)

Its score stays close to the best score here (8.2 vs 8.3), while costing about 7.8x less than Kimi K3 (max).

Detailed comparison

Metric Gemini 4 Argon Gemini 4 Argon low Release: 2026-10-13 Kimi K3 Kimi K3 max Release: 2026-07-16
Score 8.2 8.3
Rank #92 #87
Reliability 9.8 9.3
Consistency 7.9 9.3
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 79.7% 78.3%
Flaky tests 6 2
Total Runs 69 69
Cost per result 2.916 23.601
Total Cost $0.438 $3.409
Input Price $2.000 / 1M $0.830 / 1M
Output Price $10.000 / 1M $14.000 / 1M
Cache Read Price $0.100 / 1M $0.270 / 1M
Cache Write Price $0.188 / 1M N/A
Total Input Tokens 188,162 170,700
Output Tokens 6,097 7,719
Reasoning Tokens 0 225,608
Response Time (avg) 5.72s 139.41s
Response Time (max) 60.87s 766.58s
Response Time (total) 131.67s 2788.26s
Parameters ~1.2T total (~20B active) 2.8T total (104B active)
Availability Closed Weights available

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Model generation showcase

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#92 Gemini 4 Argon

low
Cost
$0.064
Time
52.8s
Tokens
6,454 tok

#87 MoonshotAI: Kimi K3

max
Cost
$0.281
Time
506.9s
Tokens
18,863 tok

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Gemini 4 Argon 10.0 10.0 100.0% 0 2.25s 8,448 498 0
Kimi K3 10.0 10.0 100.0% 0 325.79s 8,061 460 84,012

Quick Compare

Switch Comparison Pair

Gemini 4 ArgonlowvsGrok 4.5highGemini 3.5 FlashhighvsKimi K3maxGemini 4 ArgonlowvsGLM 5.2mediumGemini 4 ArgonlowvsQwen3.7 PlusmediumGemini 4 ArgonlowvsLing 3.1 FlashmediumClaude Haiku 5.5highvsKimi K3maxGemini 4 ArgonlowvsGPT-5.6 TerramediumClaude Opus 4.8mediumvsGemini 4 ArgonlowGemini 4 ArgonlowvsGPT-6 LunamediumKimi K3maxvsGPT-5.6 TerrahighKimi K3maxvsGPT-6 LunamediumClaude Opus 4.8mediumvsKimi K3max