Inkling 2 Small vs Sakana Fugu-Ultra

Change models
Inkling 2 SmallThinking Machines Lab
IndexAll categories, out of 100.
66.4 ±3.8 best
66.3 ±7.7
GapIndex points below the top.
Top
−0.1 · no clear gap
CoverageIndex weight that has results.
90% best
80%
SpeedOutput tokens per second.
—
—
EloLMArena rating and rank.
1403
—
ReleasedMonth of release.
2026-11
2026-06
Input / 1MUS dollars per 1M input tokens.
$0.30
—
Output / 1MUS dollars per 1M output tokens.
$1.00
—
1K chats2K tokens in, 500 out, each.
$1.10
—
1K documents20K tokens in, 1K out, each.
$7.00
—
1K agent tasks200K tokens in, 20K out, each.
$80.00
—
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
67.6
69.2 best
CodingCode writing and repair.
66.6
68.3 best
ReasoningLogic problems and puzzles.
68.4
68.4
MultimodalTasks with images and text.
63.6 best
62.8
KnowledgeFacts and expert knowledge.
61.5
69.7 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
60.4
—

Benchmarks

5 shared
Only Inkling 2 Small: 53Only Sakana Fugu-Ultra: 5
Inkling 2 Small
Sakana Fugu-Ultra
93.0%11 / 141
95.5% best2 / 141
85.1% best19 / 86
82.1%28 / 86
93.0%12 / 84
95.5% best2 / 84
44.1%17 / 53
50.0% best9 / 53
87.7% best15 / 49
86.6%16 / 49