AI BENCHY Compare

OpenAI: gpt-oss-120b vs Qwen: Qwen3.5-9B

Summary

gpt-oss-120b vs Qwen3.5-9B benchmark comparison: gpt-oss-120b leads on average score with 5.4 vs 4.6. Qwen3.5-9B has the lower benchmark cost at $0.006 vs $0.010. Qwen3.5-9B is faster at 1.89s vs 21.61s, with pass rates of 38.6% vs 20.6%.

Recommended model: Qwen3.5-9B - It offers the best overall trade-off: a competitive score (4.6), lower cost than gpt-oss-120b, and balanced response time.

Last updated at: 2026-06-10

Metric	gpt-oss-120b gpt-oss-120b none Release: 2025-08-05 Free Available	Qwen3.5-9B Qwen3.5-9B none Release: 2026-03-02

Metric	gpt-oss-120b gpt-oss-120b none Release: 2025-08-05 Free Available	Qwen3.5-9B Qwen3.5-9B none Release: 2026-03-02
Score	5.4	4.6
Rank	#127	#155
Reliability	10.0	10.0
Consistency	9.1	9.7
Tests Correct
Attempt pass rate	38.6%	20.6%
Flaky tests	2	1
Total Runs	57	63
Cost per result	0.168	0.123
Total Cost	$0.010	$0.006
Input Price	$0.039 / 1M	$0.100 / 1M
Output Price	$0.180 / 1M	$0.150 / 1M
Total Input Tokens	9,081	48,041
Output Tokens	51,664	3,952
Reasoning Tokens	0	0
Response Time (avg)	21.61s	1.89s
Response Time (max)	113.71s	6.03s
Response Time (total)	345.79s	39.68s

Generation showcase

Hamster playing table tennis

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

#127 gpt-oss-120b

none

No showcase result has been generated for this model yet.

Cost: $0.000
Time: -
Tokens: 0 tok

#155 Qwen3.5-9B

none

Invalid SVG

Cost: $0.000
Time: 300.0s
Tokens: 0 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

Anti-AI Tricks	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
gpt-oss-120b	6.5	10.0	50.0%	0		32.84s	1,336	8,676	0
Qwen3.5-9B	3.1	9.9	0.0%	0		1.71s	696	582	0

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
gpt-oss-120b	4.3	1.1	66.7%	1		9.57s	901	3,232	0
Qwen3.5-9B	3.9	7.8	11.1%	1		5.60s	7,913	1,042	0

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
gpt-oss-120b	3.0	10.0	0.0%	0		0ms	0	0	0
Qwen3.5-9B	3.0	10.0	0.0%	0		5.91s	20,397	1,255	0

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
gpt-oss-120b	6.5	10.0	50.0%	0		7.12s	2,421	598	0
Qwen3.5-9B	10.0	10.0	100.0%	0		847ms	7,788	249	0

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
gpt-oss-120b	3.0	10.0	0.0%	0		34.98s	1,294	29,483	0
Qwen3.5-9B	3.0	10.0	0.0%	0		464ms	789	24	0

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
gpt-oss-120b	4.8	10.0	0.0%	0		10.79s	584	615	0
Qwen3.5-9B	4.4	9.9	0.0%	0		552ms	522	99	0

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
gpt-oss-120b	9.8	10.0	100.0%	0		5.06s	1,043	1,940	0
Qwen3.5-9B	6.5	10.0	50.0%	0		514ms	711	75	0

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
gpt-oss-120b	6.0	7.2	55.6%	1		8.21s	1,188	3,982	0
Qwen3.5-9B	3.2	10.0	0.0%	0		621ms	714	347	0

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
gpt-oss-120b	3.0	10.0	0.0%	0		0ms	0	0	0
Qwen3.5-9B	10.0	10.0	100.0%	0		1.27s	8,301	273	0

Trivia	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
gpt-oss-120b	3.0	10.0	0.0%	0		47.29s	314	3,138	0
Qwen3.5-9B	3.0	10.0	0.0%	0		2.32s	210	6	0

Quick Compare

Switch Comparison Pair