AI BENCHY Compare

MiniMax: MiniMax M2.5 vs Qwen: Qwen3.5-122B-A10B

Summary

Qwen3.5-122B-A10B leads on average score with 5.3 vs 4.7. Qwen3.5-122B-A10B has the lower benchmark cost at $0.020 vs $0.303. Qwen3.5-122B-A10B is faster at 3.41s vs 65.37s, with pass rates of 46.0% vs 31.8%.

Recommended modelQwen3.5-122B-A10BIt has the best score here (5.3), while costing about 15.6x less than MiniMax M2.5 (medium).

Last updated at: 2026-07-16

Metric	MiniMax M2.5 MiniMax M2.5 medium Release: 2026-02-12	Qwen3.5-122B-A10B Qwen3.5-122B-A10B none Release: 2026-02-24

Metric	MiniMax M2.5 MiniMax M2.5 medium Release: 2026-02-12	Qwen3.5-122B-A10B Qwen3.5-122B-A10B none Release: 2026-02-24
Score	4.7	5.3
Rank	#175	#153
Reliability	10.0	10.0
Consistency	6.5	9.6
Tests Correct
Attempt pass rate	46.0%	31.8%
Flaky tests	9	1
Total Runs	63	63
Cost per result	7.900	0.393
Total Cost	$0.303	$0.020
Input Price	$0.150 / 1M	$0.260 / 1M
Output Price	$0.900 / 1M	$2.080 / 1M
Total Input Tokens	43,706	47,735
Output Tokens	109,495	3,383
Reasoning Tokens	330,814	0
Response Time (avg)	65.37s	3.41s
Response Time (max)	251.36s	46.00s
Response Time (total)	849.76s	71.59s

Generation showcase

Hamster playing table tennis

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

#175 MiniMax M2.5

medium

Invalid SVG

Cost: $0.000
Time: 300.0s
Tokens: 0 tok

#153 Qwen3.5-122B-A10B

none

Cost: $0.016
Time: 44.5s
Tokens: 6,431 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
MiniMax M2.5	7.9	6.3	83.3%	2		20.82s	612	286	45,344
Qwen3.5-122B-A10B	4.8	10.0	25.0%	0		1.59s	696	312	0

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M2.5	3.4	9.1	0.0%	0		188.58s	6,076	357	106,177
Qwen3.5-122B-A10B	3.7	7.0	22.2%	1		2.77s	7,913	693	0

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M2.5	4.5	2.1	66.7%	1		60.39s	21,104	740	9,713
Qwen3.5-122B-A10B	3.0	10.0	0.0%	0		46.00s	20,175	1,137	0

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M2.5	4.6	1.7	66.7%	2		7.48s	6,584	266	3,835
Qwen3.5-122B-A10B	10.0	10.0	100.0%	0		1.01s	7,794	243	0

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M2.5	2.9	4.4	22.2%	2		237.27s	308	105,047	133,487
Qwen3.5-122B-A10B	5.3	10.0	33.3%	0		465ms	789	15	0

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M2.5	3.8	2.5	33.3%	1		6.63s	492	25	1,686
Qwen3.5-122B-A10B	5.0	10.0	0.0%	0		1.12s	522	66	0

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M2.5	7.5	10.0	50.0%	0		621ms	699	156	1,495
Qwen3.5-122B-A10B	6.3	10.0	50.0%	0		513ms	711	69	0

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M2.5	5.3	7.2	44.4%	1		11.21s	495	1,069	9,605
Qwen3.5-122B-A10B	3.8	10.0	0.0%	0		1.00s	714	575	0

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M2.5	10.0	10.0	100.0%	0		15.35s	7,123	269	937
Qwen3.5-122B-A10B	10.0	10.0	100.0%	0		2.04s	8,211	264	0

Trivia	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M2.5	3.0	10.0	0.0%	0		80.79s	213	1,280	18,535
Qwen3.5-122B-A10B	3.0	10.0	0.0%	0		295ms	210	9	0

Quick Compare

Switch Comparison Pair

Ling-2.6-1TnonevsMiniMax M2.5medium MiniMax M2.5mediumvsGPT-5.4 Nanonone Mercury 2nonevsMiniMax M2.5medium Ring-2.6-1TnonevsMiniMax M2.5medium MiniMax M2.7mediumvsQwen3.5-122B-A10Bnone Ling-2.6-flashnonevsMiniMax M2.5medium MiniMax M2.5mediumvsNemotron 3 SupernoneFree Available MiniMax M2.5mediumvsGLM 4.7 Flashnone Mistral Small 4mediumvsQwen3.5-122B-A10Bnone KAT-Coder-Air V2.5nonevsMiniMax M2.5medium MiniMax M2.5mediumvsGPT-4o-mininone Trinity Large PreviewnonevsMiniMax M2.5medium