Granite 4.2 8B vs Mistral Small 4

Change models
IndexAll categories, out of 100.
37.6 ±5.4
37.9 ±6.2 best
GapIndex points below the top.
−0.3 · no clear gap
Top
CoverageIndex weight that has results.
85%
85%
SpeedOutput tokens per second.
101/s
114/s best
EloLMArena rating and rank.
1319
—
ReleasedMonth of release.
2026-08
2026-03
Input / 1MUS dollars per 1M input tokens.
$0.06 best
$0.15
Output / 1MUS dollars per 1M output tokens.
$0.15 best
$0.60
Batch output / 1MBatch price per 1M output tokens.
—
$0.30
1K chats2K tokens in, 500 out, each.
$0.195 best
$0.60
1K documents20K tokens in, 1K out, each.
$1.35 best
$3.60
1K agent tasks200K tokens in, 20K out, each.
$15.00 best
$42.00
ContextMaximum tokens in one request.
131K
262K best
AgenticMulti-step tasks with tools.
36.8 best
33.6
CodingCode writing and repair.
36.5
44.3 best
ReasoningLogic problems and puzzles.
37.8
39.4 best
MultimodalTasks with images and text.
—
29.1
KnowledgeFacts and expert knowledge.
33.3
39.9 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
63.2 best
34.1
MathMath problems.
41.9
—

Benchmarks

7 shared
Only Granite 4.2 8B: 13Only Mistral Small 4: 6
Granite 4.2 8B
Mistral Small 4
9.7%148 / 222
9.9% best145 / 222
45.0%164 / 217
49.7% best157 / 217
0.3%137 / 214
0.3%137 / 214
63.1%150 / 199
76.9% best109 / 199
11.8%159 / 164
21.4% best124 / 164
0.0%101 / 133
0.0%101 / 133
31.5%104 / 114
38.8% best93 / 114