Inference
EN

GPT-6.1 Terra vs MiniMax M3.1 Flash

Change models
GPT-6.1 TerraOpenAI
MiniMax M3.1 FlashMiniMax
IndexAll categories, out of 100.
77.1 ±3.8 best
69.3 ±5.4
GapIndex points below the top.
Top
−7.8
CoverageIndex weight that has results.
90% best
80%
SpeedOutput tokens per second.
46/s
100/s best
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-10
2026-10
Input / 1MUS dollars per 1M input tokens.
$1.00
$0.15 best
Output / 1MUS dollars per 1M output tokens.
$5.00
$0.60 best
Batch output / 1MBatch price per 1M output tokens.
$2.50
—
1K chats2K tokens in, 500 out, each.
$4.50
$0.60 best
1K documents20K tokens in, 1K out, each.
$25.00
$3.60 best
1K agent tasks200K tokens in, 20K out, each.
$300.00
$42.00 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
78.6 best
71.8
CodingCode writing and repair.
74.4 best
69.4
ReasoningLogic problems and puzzles.
81.3 best
67.9
MultimodalTasks with images and text.
73.2 best
58.1
KnowledgeFacts and expert knowledge.
70.5 best
68.9
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
76.9
—

Benchmarks

22 shared
Only GPT-6.1 Terra: 28Only MiniMax M3.1 Flash: 14
GPT-6.1 Terra
MiniMax M3.1 Flash
Artificial Analysis Humanity's Last ExamKnowledge
46.2%24 / 222
48.0% best17 / 222
Artificial Analysis Long Context ReasoningReasoning
82.7% best23 / 217
79.7%45 / 217
Critical Physics TasksReasoning
28.0% best16 / 214
22.3%25 / 214
Artificial Analysis Omniscience AccuracyKnowledge
47.6% best28 / 164
45.1%37 / 164
Vibe Code Bench v1.1Coding
84.0% best19 / 123
73.9%45 / 123
Artificial Analysis SciCodeCoding
55.1% best28 / 114
53.4%39 / 114
Artificial Analysis MMMU-ProMultimodal
84.7% best6 / 113
79.1%29 / 113
Legal Research BenchLegal
26.0%62 / 90
34.1% best50 / 90
Tax Agent BenchFinance
17.1%58 / 82
32.1% best23 / 82
LiveBench Data AnalysisReasoning
82.3% best4 / 80
71.4%52 / 80
LiveBench ReasoningReasoning
88.7% best20 / 80
82.9%48 / 80
Terminal-Bench 4.0Agentic
49.5% best11 / 61
25.3%28 / 61
Agent Arena steerabilityAgentic
16.6 best4 / 54
−2.636 / 54
Agent Arena task outcomeAgentic
9.7 best11 / 54
−0.734 / 54
LiveBench Coding 2.0Coding
90.8% best11 / 52
83.9%26 / 52
LiveBench DesignAgentic
82.3% best8 / 52
74.0%31 / 52
LiveBench ResearchAgentic
73.9% best25 / 52
72.7%29 / 52
LiveBench Long AgenticAgentic
39.6% best23 / 51
34.7%29 / 51
LiveBench Browser UseAgentic
100.0% best1 / 49
92.0%4 / 49
HLAB-Vals-1.1Legal
1.7%35 / 35
7.5% best24 / 35