GPT-5.1 vs MiniMax M3

Change models
GPT-5.1OpenAI
MiniMax M3MiniMax
IndexAll categories, out of 100.
55.0 ±3.7
55.0 ±2.8
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
66/s best
22/s
EloLMArena rating and rank.
1422
1427 best
ReleasedMonth of release.
2025-11
2026-06
Input / 1MUS dollars per 1M input tokens.
$1.25
$0.30 best
Output / 1MUS dollars per 1M output tokens.
$10.00
$1.20 best
Batch output / 1MBatch price per 1M output tokens.
$5.00
$0.88 best
1K chats2K tokens in, 500 out, each.
$7.50
$1.20 best
1K documents20K tokens in, 1K out, each.
$35.00
$7.20 best
1K agent tasks200K tokens in, 20K out, each.
$450.00
$84.00 best
ContextMaximum tokens in one request.
400K
1.05M best
AgenticMulti-step tasks with tools.
53.4
56.5 best
CodingCode writing and repair.
52.9
57.0 best
ReasoningLogic problems and puzzles.
55.4 best
50.0
MultimodalTasks with images and text.
57.7 best
55.9
KnowledgeFacts and expert knowledge.
56.7
60.5 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
56.3 best
54.0
MathMath problems.
56.8 best
41.3

Benchmarks

27 shared
Only GPT-5.1: 17Only MiniMax M3: 58
GPT-5.1
MiniMax M3
87.6% best65 / 220
81.3%88 / 220
28.5%84 / 216
39.0% best52 / 216
80.0%43 / 211
83.0% best18 / 211
4.9% best82 / 207
3.7%91 / 207
88.6% best70 / 203
26.7%141 / 203
87.3%55 / 193
92.9% best13 / 193
37.7%65 / 170
44.9% best42 / 170
85.7% best20 / 149
85.4%21 / 149
TaxEval v2Finance
74.9% best26 / 143
72.7%58 / 143
81.9%63 / 143
88.9% best43 / 143
86.5% best22 / 142
82.2%53 / 142
72.9%32 / 140
82.9% best1 / 140
86.6%41 / 135
92.7% best14 / 135
MMLU ProKnowledge
86.4% best42 / 135
84.2%64 / 135
16.3%84 / 132
37.1% best48 / 132
CorpFin v2Finance
63.8%39 / 131
68.1% best11 / 131
24.6%92 / 130
47.6% best79 / 130
39.9% best68 / 120
29.8%86 / 120
MedScribeHealthcare
88.1% best15 / 111
87.3%19 / 111
75.5%47 / 109
78.6% best33 / 109