Inference
EN

Gemini 3.8 Flash vs MiMo-V2.6-Pro

Change models
Gemini 3.8 FlashGoogle
MiMo-V2.6-ProXiaomi
IndexAll categories, out of 100.
67.8 ±2.5
70.2 ±4.7 best
GapIndex points below the top.
−2.4 · no clear gap
Top
CoverageIndex weight that has results.
95% best
80%
SpeedOutput tokens per second.
68/s best
31/s
EloLMArena rating and rank.
1500 best
1492
ReleasedMonth of release.
2026-09
2026-09
Input / 1MUS dollars per 1M input tokens.
$0.825
$0.435 best
Output / 1MUS dollars per 1M output tokens.
$4.13
$0.87 best
Batch output / 1MBatch price per 1M output tokens.
$1.88
—
1K chats2K tokens in, 500 out, each.
$3.71
$1.31 best
1K documents20K tokens in, 1K out, each.
$20.63
$9.57 best
1K agent tasks200K tokens in, 20K out, each.
$247.50
$104.40 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
65.3
72.1 best
CodingCode writing and repair.
66.2
66.6 best
ReasoningLogic problems and puzzles.
68.3
68.3
MultimodalTasks with images and text.
67.1
—
KnowledgeFacts and expert knowledge.
70.9 best
64.2
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
91.3
—
MathMath problems.
64.3
71.3 best

Benchmarks

49 shared
Only Gemini 3.8 Flash: 57Only MiMo-V2.6-Pro: 9
Gemini 3.8 Flash
MiMo-V2.6-Pro
Artificial Analysis Humanity's Last ExamKnowledge
47.8%20 / 222
49.4% best14 / 222
Artificial Analysis Long Context ReasoningReasoning
81.3%34 / 217
86.3% best3 / 217
Critical Physics TasksReasoning
18.3%34 / 214
26.6% best19 / 214
Artificial Analysis Omniscience AccuracyKnowledge
50.5% best19 / 164
34.8%67 / 164
GDPval-AA normalizedAgentic
46.8%34 / 133
59.2% best9 / 133
Vibe Code Bench v1.1Coding
78.7%34 / 123
85.2% best16 / 123
Artificial Analysis SciCodeCoding
56.6%23 / 114
60.9% best8 / 114
MedScribeHealthcare
84.5%34 / 109
88.3% best13 / 109
MedCodeHealthcare
48.1% best31 / 106
45.0%39 / 106
Legal Research BenchLegal
38.9%38 / 90
47.1% best16 / 90
Terminal-Bench 2.1 · BenchLMAgentic
89.4%5 / 86
89.9% best4 / 86
Tax Agent BenchFinance
32.1%23 / 82
32.4% best22 / 82
LiveBench Data AnalysisReasoning
54.0%76 / 80
72.3% best49 / 80
LiveBench ReasoningReasoning
89.3% best18 / 80
79.6%59 / 80
Finance Agent (v2)Finance
61.4% best2 / 79
57.3%16 / 79
Code MigrationCoding
36.5%35 / 77
43.0% best26 / 77
EMBFinance
72.2% best8 / 75
62.9%30 / 75
Terminal-Bench 2.1 · Vals AIAgentic
81.3% best8 / 75
67.8%32 / 75
ProgramBenchCoding
1.0% best16 / 65
0.5%19 / 65
Terminal-Bench 4.0Agentic
19.7%34 / 61
31.3% best24 / 61