GLM-5.1 vs MiniMax M3

Change models
MiniMax M3MiniMax
IndexAll categories, out of 100.
56.0 ±4.1 best
55.7 ±2.9
GapIndex points below the top.
Top
−0.3 · no clear gap
CoverageIndex weight that has results.
85%
95% best
SpeedOutput tokens per second.
102/s best
79/s
EloLMArena rating and rank.
1463 best
1428
ReleasedMonth of release.
2026-04
2026-06
Input / 1MUS dollars per 1M input tokens.
$1.40
$0.30 best
Output / 1MUS dollars per 1M output tokens.
$4.40
$1.20 best
Batch output / 1MBatch price per 1M output tokens.
—
$0.88
1K chats2K tokens in, 500 out, each.
$5.00
$1.20 best
1K documents20K tokens in, 1K out, each.
$32.40
$7.20 best
1K agent tasks200K tokens in, 20K out, each.
$368.00
$84.00 best
ContextMaximum tokens in one request.
205K
1.05M best
AgenticMulti-step tasks with tools.
59.2 best
57.4
CodingCode writing and repair.
57.0
57.7 best
ReasoningLogic problems and puzzles.
50.9 best
50.5
MultimodalTasks with images and text.
—
56.5
KnowledgeFacts and expert knowledge.
51.7
61.0 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
60.3 best
54.7
MathMath problems.
54.9 best
41.6

Benchmarks

36 shared
Only GLM-5.1: 24Only MiniMax M3: 48
GLM-5.1
MiniMax M3
30.1%79 / 222
39.0% best52 / 222
73.7%100 / 217
83.0% best18 / 217
89.9% best41 / 217
81.3%85 / 217
4.6% best87 / 214
3.7%93 / 214
93.3% best51 / 200
26.7%138 / 200
86.8%61 / 199
92.9% best13 / 199
23.7%111 / 164
44.9% best38 / 164
84.4%33 / 149
85.4% best21 / 149
97.7% best9 / 149
88.9%45 / 149
76.3%13 / 146
82.9% best1 / 146
TaxEval v2Finance
71.2%80 / 143
72.7% best58 / 143
81.4%62 / 142
82.2% best53 / 142
84.5%50 / 135
92.7% best14 / 135
MMLU ProKnowledge
86.9% best37 / 135
84.2%64 / 135
30.8%62 / 133
37.1% best48 / 133
CorpFin v2Finance
64.5%35 / 131
68.1% best11 / 131
31.5%81 / 123
47.6% best72 / 123
44.8%74 / 114
47.1% best65 / 114
MedScribeHealthcare
72.3%89 / 109
87.3% best18 / 109
MedCodeHealthcare
41.6%52 / 106
46.3% best37 / 106