Navigate
Advertise here

Mistral Small 4 (medium) vs Nemotron 3.5 Lightning (high)

Nemotron 3.5 Lightning (high) leads on average score with 5.2 vs 5.1. Mistral Small 4 (medium) has the lower benchmark cost at $0.126 vs $0.168. Mistral Small 4 (medium) is faster at 12.68s vs 77.08s, with pass rates of 42.0% vs 47.8%.

Last updated at: 2026-11-13

Compared models

Rank
#389
Total Output Tokens
127,970
Response Time (avg)
12.68s
Total Cost
$0.126
Rank
#385
Total Output Tokens
626,081
Response Time (avg)
77.08s
Total Cost
$0.168
Recommended model Mistral Small 4 (medium)

Its score stays close to the best score here (5.1 vs 5.2), while responding about 6.1x faster than Nemotron 3.5 Lightning (high).

Detailed comparison

Metric Mistral Small 4 Mistral Small 4 medium Release: 2026-03-16 Nemotron 3.5 Lightning Nemotron 3.5 Lightning high Release: 2026-08-11 Free Available
Score 5.1 5.2
Rank #389 #385
Reliability 9.7 9.6
Consistency 7.1 5.7
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 42.0% 47.8%
Flaky tests 8 12
Total Runs 69 69
Cost per result 2.502 0.000
Total Cost $0.126 $0.168
Input Price $0.150 / 1M $0.060 / 1M
Output Price $0.600 / 1M $0.160 / 1M
Cache Read Price $0.015 / 1M $0.030 / 1M
Cache Write Price N/A N/A
Total Input Tokens 321,955 170,517
Output Tokens 41,555 149,968
Reasoning Tokens 94,946 509,725
Response Time (avg) 12.68s 77.08s
Response Time (max) 59.15s 490.99s
Response Time (total) 291.66s 1772.78s
Parameters 119B total (6B active) 30B total (3B active)
Availability Open source 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.

#389 Mistral Small 4

medium
Cost
$0.006
Time
47.9s
Tokens
9,857 tok

#385 Nemotron 3.5 Lightning

high
Cost
$0.000
Time
92.8s
Tokens
11,343 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
Mistral Small 4 4.4 5.1 33.3% 2 39.98s 7,636 11,635 54,715
Nemotron 3.5 Lightning 4.4 5.1 33.3% 2 168.41s 7,623 68,533 242,319

Switch Comparison Pair