MiniMax M3 (medium) vs Qwen3.8 2.4T A95B (high)

Recommended model MiniMax M3 (medium)

It has the best score here (7.5), while costing about 7.9x less than Qwen3.8 2.4T A95B (high).

Detailed comparison

Metric	MiniMax M3 MiniMax M3 medium Release: 2026-06-01	Qwen3.8 2.4T A95B Qwen3.8 2.4T A95B high Release: 2026-08-12

Metric	MiniMax M3 MiniMax M3 medium Release: 2026-06-01	Qwen3.8 2.4T A95B Qwen3.8 2.4T A95B high Release: 2026-08-12
Score	7.5	7.4
Rank	#84	#95
Reliability	9.7	9.4
Consistency	8.0	8.3
Attempts	66/66	66/66
Tests Correct
Attempt pass rate	62.1%	74.2%
Flaky tests	5	4
Total Runs	66	66
Cost per result	2.724	16.832
Total Cost	$0.300	$2.357
Input Price	$0.300 / 1M	$2.000 / 1M
Output Price	$1.200 / 1M	$6.000 / 1M
Total Input Tokens	121,996	108,931
Output Tokens	90,051	112,801
Reasoning Tokens	185,731	343,227
Response Time (avg)	75.15s	120.59s
Response Time (max)	431.03s	532.28s
Response Time (total)	1578.24s	2653.05s
Parameters	428B total (23B active)	2.4T total (95B active)
Availability	Weights available	Weights available

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

medium

high

Invalid SVG

Category:

Anti-AI Tricks	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M3	5.5	3.7	66.7%	3		14.95s	2,526	874	3,414
Qwen3.8 2.4T A95B	10.0	10.0	100.0%	0		24.22s	1,128	305	4,864

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M3	6.1	6.5	55.6%	1		144.74s	5,804	6,223	32,667
Qwen3.8 2.4T A95B	5.9	6.3	55.6%	1		160.52s	6,399	3,310	48,078

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M3	10.0	10.0	100.0%	0		138.24s	90,204	30,186	87,263
Qwen3.8 2.4T A95B	6.9	5.9	66.7%	1		266.12s	81,205	7,791	41,921

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M3	10.0	10.0	100.0%	0		14.92s	8,088	514	3,164
Qwen3.8 2.4T A95B	10.0	10.0	100.0%	0		13.67s	7,928	550	2,307

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M3	3.2	9.3	0.0%	0		234.97s	875	28,389	31,248
Qwen3.8 2.4T A95B	4.1	6.5	22.2%	1		301.08s	964	11,279	139,028

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M3	5.1	3.4	33.3%	1		33.25s	954	2,487	2,523
Qwen3.8 2.4T A95B	6.1	3.1	66.7%	1		11.38s	630	2,020	2,165

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M3	9.8	10.0	100.0%	0		6.14s	1,623	103	920
Qwen3.8 2.4T A95B	9.8	10.0	100.0%	0		11.45s	927	245	1,727

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M3	7.9	9.9	66.7%	0		49.91s	2,079	11,946	13,761
Qwen3.8 2.4T A95B	10.0	10.0	100.0%	0		65.54s	989	698	15,073

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M3	10.0	10.0	100.0%	0		11.91s	9,168	281	555
Qwen3.8 2.4T A95B	10.0	10.0	100.0%	0		32.93s	8,481	302	656

Trivia	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
MiniMax M3	3.0	10.0	0.0%	0		100.80s	675	9,048	10,216
Qwen3.8 2.4T A95B	3.0	10.0	0.0%	0		347.95s	280	86,301	87,408

Switch Comparison Pair