Granite 4.2 8B vs Ling 2.6 Flash

Change models
Ling 2.6 FlashInclusionAI
IndexAll categories, out of 100.
37.5 ±5.4 best
37.1 ±7.9
GapIndex points below the top.
Top
−0.4 · no clear gap
CoverageIndex weight that has results.
85% best
75%
SpeedOutput tokens per second.
111/s best
104/s
EloLMArena rating and rank.
1319
—
ReleasedMonth of release.
2026-08
2026-04
Input / 1MUS dollars per 1M input tokens.
$0.06
—
Output / 1MUS dollars per 1M output tokens.
$0.15
—
1K chats2K tokens in, 500 out, each.
$0.195
—
1K documents20K tokens in, 1K out, each.
$1.35
—
1K agent tasks200K tokens in, 20K out, each.
$15.00
—
ContextMaximum tokens in one request.
131K
262K best
AgenticMulti-step tasks with tools.
36.6
47.0 best
CodingCode writing and repair.
36.4 best
31.2
ReasoningLogic problems and puzzles.
37.6 best
32.8
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
33.7 best
31.4
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
62.1 best
42.3
MathMath problems.
42.0
—

Benchmarks

9 shared
Only Granite 4.2 8B: 11Only Ling 2.6 Flash: 2
Granite 4.2 8B
Ling 2.6 Flash
9.7% best142 / 216
6.3%162 / 216
45.0% best158 / 211
31.3%173 / 211
0.3% best132 / 207
0.0%145 / 207
63.1% best144 / 193
59.3%151 / 193
11.8%164 / 170
15.6% best154 / 170
64.1% best106 / 144
59.0%115 / 144
0.0%100 / 132
0.0%100 / 132
79.3% best16 / 57
57.0%46 / 57
36.1% best27 / 35
27.0%33 / 35