AI BENCHY Compare

OpenAI: GPT-5.5 vs Qwen: Qwen3.7 Max

Summary

The average score is effectively tied at 9.3 vs 9.4. Qwen3.7 Max (medium) has the lower benchmark cost at $0.523 vs $0.907. GPT-5.5 (low) is faster at 9.76s vs 16.02s, with pass rates of 85.7% vs 88.9%.

Recommended modelQwen3.7 Max (medium)It has the best score here (9.4), while costing about 1.7x less than GPT-5.5 (low).

Last updated at: 2026-07-14

Metric	GPT-5.5 GPT-5.5 low Release: 2026-04-24	Qwen3.7 Max Qwen3.7 Max medium Release: 2026-05-22

Metric	GPT-5.5 GPT-5.5 low Release: 2026-04-24	Qwen3.7 Max Qwen3.7 Max medium Release: 2026-05-22
Score	9.3	9.4
Rank	#7	#4
Reliability	10.0	10.0
Consistency	10.0	9.6
Tests Correct
Attempt pass rate	85.7%	88.9%
Flaky tests	0	1
Total Runs	63	63
Cost per result	5.035	5.517
Total Cost	$0.907	$0.523
Input Price	$5.000 / 1M	$1.250 / 1M
Output Price	$30.000 / 1M	$3.750 / 1M
Total Input Tokens	34,209	42,360
Output Tokens	2,046	2,129
Reasoning Tokens	22,460	122,959
Response Time (avg)	9.76s	16.02s
Response Time (max)	56.19s	59.98s
Response Time (total)	204.92s	336.51s

Generation showcase

Hamster playing table tennis

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

#7 GPT-5.5

low

Cost: $0.068
Time: 37.0s
Tokens: 2,339 tok

#4 Qwen3.7 Max

medium

Cost: $0.017
Time: 68.8s
Tokens: 4,526 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

Category:

Anti-AI Tricks	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.5	10.0	10.0	100.0%	0		4.41s	606	238	1,020
Qwen3.7 Max	10.0	10.0	100.0%	0		6.36s	672	222	8,742

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.5	10.0	10.0	100.0%	0		15.04s	7,302	423	6,402
Qwen3.7 Max	10.0	10.0	100.0%	0		35.31s	7,893	423	34,808

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.5	10.0	10.0	100.0%	0		9.56s	11,019	303	717
Qwen3.7 Max	10.0	10.0	100.0%	0		19.60s	14,934	366	8,405

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.5	10.0	10.0	100.0%	0		3.28s	7,140	228	157
Qwen3.7 Max	10.0	10.0	100.0%	0		8.80s	7,782	270	6,254

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.5	5.3	10.0	33.3%	0		28.05s	723	69	11,609
Qwen3.7 Max	5.9	7.2	55.6%	1		24.94s	771	61	31,793

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.5	10.0	10.0	100.0%	0		5.17s	477	133	245
Qwen3.7 Max	10.0	10.0	100.0%	0		11.70s	516	135	4,457

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.5	9.9	10.0	100.0%	0		3.74s	660	93	415
Qwen3.7 Max	10.0	10.0	100.0%	0		7.46s	699	102	5,452

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.5	10.0	10.0	100.0%	0		4.74s	642	279	954
Qwen3.7 Max	10.0	10.0	100.0%	0		8.84s	696	259	8,908

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.5	10.0	10.0	100.0%	0		4.96s	5,445	250	101
Qwen3.7 Max	10.0	10.0	100.0%	0		6.63s	8,193	267	1,220

Trivia	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.5	3.0	10.0	0.0%	0		10.06s	195	30	840
Qwen3.7 Max	3.0	10.0	0.0%	0		33.37s	204	24	12,920

Quick Compare

Switch Comparison Pair

GPT-5.6 SolhighvsQwen3.7 Maxmedium Claude Fable 5mediumvsGPT-5.5low Gemini 3.5 FlashlowvsQwen3.7 Maxmedium Gemini 3.1 Pro PreviewmediumvsGPT-5.5low GPT-5.6 SollowvsQwen3.7 Maxmedium Gemini 3.5 FlashmediumvsGPT-5.5low Gemini 3 Flash PreviewmediumvsGPT-5.5low GPT-5.5lowvsQwen3.6 Max Previewmedium Gemini 3.5 FlashhighvsQwen3.7 Maxmedium Claude Opus 4.8mediumvsGPT-5.5low Gemini 3.5 FlashhighvsGPT-5.5low Claude Opus 4.7mediumvsGPT-5.5low