Navigate
AI BENCHY
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com

Qwen: Qwen3.5-35B-A3B vs Thinking Machines: Inkling

Qwen3.5-35B-A3B (medium) leads on average score with 6.2 vs 6.1. Inkling (low) has the lower benchmark cost at $0.187 vs $0.837. Inkling (low) is faster at 5.15s vs 112.47s, with pass rates of 66.7% vs 54.6%.

Recommended modelInkling (low)Its score stays close to the best score here (6.1 vs 6.2), while costing about 4.5x less than Qwen3.5-35B-A3B (medium).

Last updated at: 2026-07-18

Metric Qwen3.5-35B-A3B Qwen3.5-35B-A3B medium Release: 2026-02-24 Inkling Inkling low Release: 2026-07-18
Score 6.2 6.1
Rank #115 #119
Reliability 10.0 9.9
Consistency 7.6 8.6
Tests Correct
Attempt pass rate 66.7% 54.6%
Flaky tests 6 4
Total Runs 66 66
Cost per result 9.130 1.866
Total Cost $0.837 $0.187
Input Price $0.140 / 1M $1.000 / 1M
Output Price $1.000 / 1M $4.050 / 1M
Total Input Tokens 130,388 109,884
Output Tokens 40,630 8,579
Reasoning Tokens 786,040 10,343
Response Time (avg) 112.47s 5.15s
Response Time (max) 950.25s 41.58s
Response Time (total) 2474.28s 113.39s

Hamster playing table tennis

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

#115 Qwen3.5-35B-A3B

medium
Cost
$0.009
Time
71.4s
Tokens
8,631 tok

#119 Thinking Machines: Inkling

low
Cost
$0.002
Time
6.1s
Tokens
502 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
Qwen3.5-35B-A3B 5.9 9.3 33.3% 0 206.65s 4,106 23,844 111,462
Inkling 5.1 7.2 22.2% 1 8.71s 7,374 355 4,961

Quick Compare

Switch Comparison Pair