Inference
EN

GPT-6.1 Terra vs MiMo-V2.6-Pro

Change models
GPT-6.1 TerraOpenAI
MiMo-V2.6-ProXiaomi
IndexAll categories, out of 100.
77.1 ±3.8 best
70.2 ±4.7
GapIndex points below the top.
Top
−6.9
CoverageIndex weight that has results.
90% best
80%
SpeedOutput tokens per second.
46/s best
31/s
EloLMArena rating and rank.
—
1492
ReleasedMonth of release.
2026-10
2026-09
Input / 1MUS dollars per 1M input tokens.
$1.00
$0.435 best
Output / 1MUS dollars per 1M output tokens.
$5.00
$0.87 best
Batch output / 1MBatch price per 1M output tokens.
$2.50
—
1K chats2K tokens in, 500 out, each.
$4.50
$1.31 best
1K documents20K tokens in, 1K out, each.
$25.00
$9.57 best
1K agent tasks200K tokens in, 20K out, each.
$300.00
$104.40 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
78.6 best
72.1
CodingCode writing and repair.
74.4 best
66.6
ReasoningLogic problems and puzzles.
81.3 best
68.3
MultimodalTasks with images and text.
73.2
—
KnowledgeFacts and expert knowledge.
70.5 best
64.2
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
76.9 best
71.3

Benchmarks

25 shared
Only GPT-6.1 Terra: 25Only MiMo-V2.6-Pro: 33
GPT-6.1 Terra
MiMo-V2.6-Pro
Artificial Analysis Humanity's Last ExamKnowledge
46.2%24 / 222
49.4% best14 / 222
Artificial Analysis Long Context ReasoningReasoning
82.7%23 / 217
86.3% best3 / 217
Critical Physics TasksReasoning
28.0% best16 / 214
26.6%19 / 214
Artificial Analysis Omniscience AccuracyKnowledge
47.6% best28 / 164
34.8%67 / 164
Vibe Code Bench v1.1Coding
84.0%19 / 123
85.2% best16 / 123
Artificial Analysis SciCodeCoding
55.1%28 / 114
60.9% best8 / 114
Legal Research BenchLegal
26.0%62 / 90
47.1% best16 / 90
Tax Agent BenchFinance
17.1%58 / 82
32.4% best22 / 82
LiveBench Data AnalysisReasoning
82.3% best4 / 80
72.3%49 / 80
LiveBench ReasoningReasoning
88.7% best20 / 80
79.6%59 / 80
Terminal-Bench 4.0Agentic
49.5% best11 / 61
31.3%24 / 61
Agent Arena steerabilityAgentic
16.6 best4 / 54
1.525 / 54
Agent Arena task outcomeAgentic
9.7 best11 / 54
5.016 / 54
LiveBench Coding 2.0Coding
90.8% best11 / 52
81.5%30 / 52
LiveBench DesignAgentic
82.3% best8 / 52
78.5%18 / 52
LiveBench ResearchAgentic
73.9%25 / 52
76.7% best22 / 52
LiveBench Long AgenticAgentic
39.6%23 / 51
47.5% best16 / 51
LiveBench Browser UseAgentic
100.0% best1 / 49
88.0%8 / 49
HLAB-Vals-1.1Legal
1.7%35 / 35
13.8% best13 / 35
Artificial Analysis AutomationBenchAgentic
60.2% best12 / 23
58.6%15 / 23