Granite 4.2 8B (medium) vs Mistral Small 4 (medium)

Recommended model Mistral Small 4 (medium)

It has the best score here (5.1), while responding about 4.3x faster than Granite 4.2 8B (medium).

Detailed comparison

Metric	Granite 4.2 8B Granite 4.2 8B medium Release: 2026-09-02	Mistral Small 4 Mistral Small 4 medium Release: 2026-03-16

Metric	Granite 4.2 8B Granite 4.2 8B medium Release: 2026-09-02	Mistral Small 4 Mistral Small 4 medium Release: 2026-03-16
Score	5.2	5.1
Rank	#243	#246
Reliability	8.7	10.0
Consistency	9.6	7.0
Attempts	66/66	66/66
Tests Correct
Attempt pass rate	34.9%	43.9%
Flaky tests	1	8
Total Runs	66	66
Cost per result	0.117	1.923
Total Cost	$0.009	$0.097
Input Price	$0.100 / 1M	$0.150 / 1M
Output Price	$0.150 / 1M	$0.600 / 1M
Total Input Tokens	52,909	140,559
Output Tokens	7,058	40,268
Reasoning Tokens	12,272	93,329
Response Time (avg)	45.97s	10.80s
Response Time (max)	557.96s	59.15s
Response Time (total)	1011.42s	237.60s
Parameters	8B	119B total (6B active)
Availability	Open source	Open source

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

medium

Provider returned error

medium

Category:

Anti-AI Tricks	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Granite 4.2 8B	8.4	10.0	75.0%	0		10.34s	777	1,452	889
Mistral Small 4	5.6	3.8	66.7%	3		2.67s	708	4,055	4,778

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Granite 4.2 8B	5.5	10.0	33.3%	0		12.09s	8,439	2,445	3,900
Mistral Small 4	4.4	5.1	33.3%	2		39.98s	7,636	11,635	54,715

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Granite 4.2 8B	3.0	10.0	0.0%	0		291.12s	24,807	1,902	6,258
Mistral Small 4	3.0	10.0	0.0%	0		32.40s	116,624	17,890	18,384

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Granite 4.2 8B	6.5	10.0	50.0%	0		1.43s	7,683	270	75
Mistral Small 4	7.3	5.9	83.3%	1		1.23s	6,171	335	723

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Granite 4.2 8B	5.3	10.0	33.3%	0		13.96s	876	154	290
Mistral Small 4	5.9	7.2	55.6%	1		6.33s	807	3,427	7,871

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Granite 4.2 8B	4.0	10.0	0.0%	0		605ms	561	102	24
Mistral Small 4	4.8	10.0	0.0%	0		2.05s	519	821	828

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Granite 4.2 8B	3.8	6.0	33.3%	1		36.86s	636	127	425
Mistral Small 4	7.3	5.8	83.3%	1		1.38s	729	540	1,031

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Granite 4.2 8B	3.1	10.0	0.0%	0		75.99s	469	206	56
Mistral Small 4	3.4	9.7	0.0%	0		2.17s	735	1,226	2,632

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Granite 4.2 8B	10.0	10.0	100.0%	0		2.28s	8,412	359	214
Mistral Small 4	10.0	10.0	100.0%	0		3.50s	6,420	321	810

Trivia	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Granite 4.2 8B	3.0	10.0	0.0%	0		2.24s	249	41	141
Mistral Small 4	3.0	10.0	0.0%	0		5.92s	210	18	1,557

Switch Comparison Pair