Navigate
AI BENCHY
Advertise here

GPT-5 Nano (medium) vs Qwen3.5-35B-A3B

The average score is effectively tied at 6.0 vs 5.9. GPT-5 Nano (medium) has the lower benchmark cost at $0.118 vs $0.142. Qwen3.5-35B-A3B is faster at 12.73s vs 54.20s, with pass rates of 54.5% vs 39.4%.

Last updated at: 2026-08-29

Rank
#188
Total Output Tokens
282,437
Response Time (avg)
54.20s
Total Cost
$0.118
Rank
#190
Total Output Tokens
86,616
Response Time (avg)
12.73s
Total Cost
$0.142
Recommended model Qwen3.5-35B-A3B

It has the best score here (5.9), while responding about 4.3x faster than GPT-5 Nano (medium).

Detailed comparison

Metric GPT-5 Nano GPT-5 Nano medium Release: 2025-08-07 Qwen3.5-35B-A3B Qwen3.5-35B-A3B none Release: 2026-02-24
Score 6.0 5.9
Rank #188 #190
Reliability 10.0 10.0
Consistency 6.6 8.6
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 54.5% 39.4%
Flaky tests 9 4
Total Runs 66 66
Cost per result 1.472 1.841
Total Cost $0.118 $0.142
Input Price $0.050 / 1M $0.250 / 1M
Output Price $0.400 / 1M $1.250 / 1M
Total Input Tokens 94,944 134,530
Output Tokens 12,037 86,616
Reasoning Tokens 270,400 0
Response Time (avg) 54.20s 12.73s
Response Time (max) 227.89s 209.15s
Response Time (total) 867.23s 279.97s
Parameters ~120B total (~5B active) 35B total (3B active)
Availability Closed Open source

Model generation showcase

Hamster playing table tennis

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

#188 GPT-5 Nano

medium
Cost
$0.006
Time
108.5s
Tokens
13,209 tok

#190 Qwen3.5-35B-A3B

none
Cost
$0.005
Time
28.4s
Tokens
4,518 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
GPT-5 Nano 7.0 7.7 55.6% 1 41.62s 7,305 740 41,152
Qwen3.5-35B-A3B 5.5 10.0 33.3% 0 1.39s 7,808 571 0

Quick Compare

Switch Comparison Pair