Gemini 3 Flash vs Inkling

Change models
InklingThinking Machines Lab
IndexAll categories, out of 100.
55.0 ±4.0 best
54.8 ±2.9
GapIndex points below the top.
Top
−0.2 · no clear gap
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
198/s best
85/s
EloLMArena rating and rank.
1466 best
1444
ReleasedMonth of release.
2025-12
2026-07
Input / 1MUS dollars per 1M input tokens.
$0.50 best
$1.00
Output / 1MUS dollars per 1M output tokens.
$3.00 best
$4.05
1K chats2K tokens in, 500 out, each.
$2.50 best
$4.03
1K documents20K tokens in, 1K out, each.
$13.00 best
$24.05
1K agent tasks200K tokens in, 20K out, each.
$160.00 best
$281.00
ContextMaximum tokens in one request.
1M best
524K
AgenticMulti-step tasks with tools.
48.5
51.2 best
CodingCode writing and repair.
56.8 best
54.1
ReasoningLogic problems and puzzles.
50.8
56.1 best
MultimodalTasks with images and text.
67.3 best
55.0
KnowledgeFacts and expert knowledge.
60.7 best
57.1
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
40.5
66.0 best
MathMath problems.
57.3 best
54.1

Benchmarks

13 shared
Only Gemini 3 Flash: 18Only Inkling: 65
Gemini 3 Flash
Inkling
15.0%127 / 222
31.9% best72 / 222
55.3%147 / 217
77.3% best77 / 217
89.4% best47 / 217
88.3%56 / 217
1.4%113 / 214
5.4% best81 / 214
95.6% best40 / 200
88.9%63 / 200
81.2%95 / 199
87.2% best59 / 199
45.8% best34 / 164
39.3%56 / 164
78.6% best33 / 113
73.5%63 / 113
66.8% best13 / 91
40.3%54 / 91
Chess PuzzlesReasoning
40.0% best36 / 90
21.0%59 / 90
51.2% best54 / 90
33.3%66 / 90
17.1% best52 / 72
4.9%62 / 72
27.3% best16 / 28
25.0%20 / 28