Gemini 3.1 Flash Lite Preview vs MiniMax M2.1

Change models
IndexAll categories, out of 100.
49.1 ±6.9 best
48.7 ±8.9
GapIndex points below the top.
Top
−0.4 · no clear gap
CoverageIndex weight that has results.
80% best
65%
SpeedOutput tokens per second.
116/s best
34/s
EloLMArena rating and rank.
1416
—
ReleasedMonth of release.
2026-03
2025-12
Input / 1MUS dollars per 1M input tokens.
$0.25 best
$0.30
Output / 1MUS dollars per 1M output tokens.
$1.50
$1.20 best
1K chats2K tokens in, 500 out, each.
$1.25
$1.20 best
1K documents20K tokens in, 1K out, each.
$6.50 best
$7.20
1K agent tasks200K tokens in, 20K out, each.
$80.00 best
$84.00
ContextMaximum tokens in one request.
1.05M best
205K
AgenticMulti-step tasks with tools.
41.0
48.2 best
CodingCode writing and repair.
47.9
51.1 best
ReasoningLogic problems and puzzles.
—
—
MultimodalTasks with images and text.
61.7
—
KnowledgeFacts and expert knowledge.
51.9 best
51.3
MultilingualTasks in many languages.
57.0
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
51.3 best
43.3

Benchmarks

13 shared
Only Gemini 3.1 Flash Lite Preview: 18Only MiniMax M2.1: 5
Gemini 3.1 Flash Lite Preview
MiniMax M2.1
83.8% best47 / 149
75.4%115 / 149
TaxEval v2Finance
71.8% best72 / 143
66.4%112 / 143
80.1%70 / 142
81.8% best59 / 142
81.1% best64 / 135
78.5%72 / 135
MMLU ProKnowledge
86.2%45 / 135
87.0% best35 / 135
CorpFin v2Finance
59.4% best78 / 131
58.9%81 / 131
MedScribeHealthcare
63.9%104 / 111
80.8% best57 / 111
MedCodeHealthcare
47.6% best32 / 108
34.1%82 / 108
AIMEMath
83.3% best43 / 95
77.9%49 / 95
SWE-benchCoding
62.8%74 / 87
74.8% best47 / 87
24.7%52 / 66
37.1% best38 / 66
55.0%35 / 53
55.8% best32 / 53
46.1% best33 / 51
33.4%44 / 51