BenchLeader

GPT-5.2 vs MiMo-V2.6-Pro

Full profiles: GPT-5.2 (OpenAI) and MiMo-V2.6-Pro (Xiaomi): every benchmark, price and rank.

Updated · Data from 9 sources

As of 16 Nov 2026, GPT-5.2 and MiMo-V2.6-Pro are neck and neck on quality (59.9 vs 57.5 on the BenchLeader Index, inside the ±5.7 margin), and MiMo-V2.6-Pro is 8.8× cheaper at $0.544 vs $4.81 per 1M tokens blended. Choose GPT-5.2 for knowledge (56 vs 42), reasoning (60 vs 50), and coding (63 vs 59); choose MiMo-V2.6-Pro for fast first answers (42.3 s vs 112.5 s) and maths (66 vs 57), agents & tools (57 vs 54), and long context (68 vs 66).

Key facts (as of 16 Nov 2026)

  • GPT-5.2 scores 59.9 on the BenchLeader Index and MiMo-V2.6-Pro scores 57.5 (BenchLeader, 16 Nov 2026).
  • GPT-5.2 costs $4.81 per 1M tokens blended (list price, 16 Nov 2026).
  • MiMo-V2.6-Pro costs $0.544 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 9 benchmarks both models have, MiMo-V2.6-Pro leads 8 (BenchLeader, 16 Nov 2026).

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
CodingGPT-5.263 vs 59 category score; Vibe Code Bench v1.1 53.5% vs 85.2%Medium
Agents & tool useMiMo-V2.6-Pro57 vs 54 category scoreMedium
MathsMiMo-V2.6-Pro66 vs 57 category score; ProofBench 70.0% vs 15.0%High
ReasoningGPT-5.260 vs 50 category score; Humanity's Last Exam (AA) 37.7% vs 49.4%High
KnowledgeGPT-5.256 vs 42 category score; MedCode 49.8% vs 45.0%High
Long documentsMiMo-V2.6-Pro68 vs 66 category score; AA-LCR v1.1 86.3% vs 82.7%Medium
Chat quality (human preference)–Only MiMo-V2.6-Pro has an Arena rating (67 category score)Not comparable
Lowest costMiMo-V2.6-Pro$0.548 vs $4.81 per 1M blended; agentic coding session $0.030 vs $0.161–
Fastest first answerMiMo-V2.6-Pro42.3 s (MiMo-V2.6-Pro) vs 112.5 s (GPT-5.2 (xhigh)) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • GPT-5.2 (xhigh) and MiMo-V2.6-Pro are neck and neck on quality (59.9 vs 57.5, within the ±5.7 margin).
  • GPT-5.2 (xhigh) is stronger in coding, knowledge, reasoning.
  • MiMo-V2.6-Pro is stronger in agents & tools, long context, maths.
  • MiMo-V2.6-Pro is 8.8× cheaper ($0.544 vs $4.81 per 1M blended).
  • GPT-5.2 (xhigh) streams 1.4× faster (76 vs 54 tokens per second).

At a glance

SpecGPT-5.2MiMo-V2.6-Pro
DeveloperOpenAIXiaomi
Released11 Dec 202521 Sep 2026
Context window (tokens)400,0001,048,576
Compared atGPT-5.2 (xhigh)MiMo-V2.6-Pro
Open weightsNoYes
Price in / out / cached input per 1M$1.75 / $14.00 / $0.175$0.440 / $0.870 / $0.0036

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryGPT-5.2 (xhigh)MiMo-V2.6-ProLeader
Reasoning60.449.9GPT-5.2
Coding63.058.8GPT-5.2
Agents & tools53.857.1MiMo-V2.6-Pro
Maths56.565.5MiMo-V2.6-Pro
Knowledge56.142.3GPT-5.2
Instruction following73.7–not comparable
Human preference–67.0not comparable
Multimodal–60.2not comparable
Long context66.067.9MiMo-V2.6-Pro

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingAgents & toolsMathsKnowledgeLong contextGPT-5.2, Reasoning: 60.4GPT-5.2, Coding: 63.0GPT-5.2, Agents & tools: 53.8GPT-5.2, Maths: 56.5GPT-5.2, Knowledge: 56.1GPT-5.2, Long context: 66.0MiMo-V2.6-Pro, Reasoning: 49.9MiMo-V2.6-Pro, Coding: 58.8MiMo-V2.6-Pro, Agents & tools: 57.1MiMo-V2.6-Pro, Maths: 65.5MiMo-V2.6-Pro, Knowledge: 42.3MiMo-V2.6-Pro, Long context: 67.9

Not drawn, measured for fewer than two of these models: Instruction following, Multimodal, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 9 benchmarks both have, GPT-5.2 leads 1, MiMo-V2.6-Pro leads 8. Every overall index that rates both puts MiMo-V2.6-Pro ahead.

Overall indexGPT-5.2 (xhigh)MiMo-V2.6-ProLeader
BenchLeader Index59.957.5neck and neck
Arena Text1437†1480MiMo-V2.6-Pro

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureGPT-5.2 (xhigh)MiMo-V2.6-Pro
Blended price per 1M tokens$4.81$0.548
Input / output per 1M$1.75 / $14.00$0.440 / $0.870
Cached input per 1M$0.175$0.0036
Price per task: chat reply$0.0049$0.0004
Price per task: summarize a 30-page report$0.029$0.0058
Price per task: code edit$0.032$0.0039
Price per task: agentic coding session$0.161$0.030
Price per task: structured extraction$0.0063$0.0011
Agentic coding session, input mostly cached$0.090$0.010
Cost per benchmark task (AA Index)–$0.257
Output tokens per task (AA Index)–121k
Of which reasoning–86k
Time per task (AA Index)–38 min
Output speed76 tok/s54 tok/s
Time to first answer112.5 s42.3 s
Time to a complete answer, last measured 13 Nov 2026154.4 s95.7 s

Each model is compared at its best-ranked reasoning-effort setting. GPT-5.2 (xhigh) scores 59.9 and takes 112 s to its first answer token; GPT-5.2 scores 56.7 in 2 s, GPT-5.2 (medium) scores 56.2 in 7 s. MiMo-V2.6-Pro scores 57.5 and takes 42 s to its first answer token. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

180 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherGPT-5.2 (xhigh)MiMo-V2.6-Pro
BenchLeader IndexBenchLeader59.957.5
Agents & tools scoreBenchLeader53.857.1
Coding scoreBenchLeader63.058.8
Instruction following scoreBenchLeader73.7–
Knowledge scoreBenchLeader56.142.3
Long context scoreBenchLeader66.067.9
Maths scoreBenchLeader56.565.5
Reasoning scoreBenchLeader60.449.9
Human preference scoreBenchLeader–67.0
Multimodal scoreBenchLeader–60.2
Blended price $/MBenchLeader$4.81$0.548
Output speedBenchLeader76 tok/s54 tok/s
Time to first answerBenchLeader112.5 s42.3 s
Context windowBenchLeader400,000 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub91.4%–
Humanity's Last ExamScale AI / CAIS27.8%†–
SimpleBenchSimpleBench45.8%†–
Arena Hard PromptsArena (LMArena)1497†1504
LiveBench 2.0 ReasoningLiveBench–79.6%†
LiveBench 1.0 ReasoningLiveBench83.2%†–
GPQA Diamond (AA)Artificial Analysis90.3%–
Humanity's Last Exam (AA)Artificial Analysis37.7%49.4%
HLE-Diamond (AA)Artificial Analysis–15.2%
GPQA Diamond (Vals)Vals AI91.7%–
Kagi LLM BenchmarkKagi LLM Benchmark73.3%†–
ARC-AGI-1ARC Prize86.2%–
ARC-AGI-2ARC Prize52.9%–
CritPtArtificial Analysis11.6%26.6%
CritPt v2 hard subset (AA)Artificial Analysis–34.0%
MysteryMechanismVals AI–15.3%
SciPredictScale AI SEAL20.6%†–
Arena ExpertArena (LMArena)1491†1526
Chess PuzzlesEpoch AI Benchmarking Hub48.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub22.0%†–
CL-benchEpoch AI Benchmarking Hub18.2%†–
LMCAEpoch AI Benchmarking Hub43.9%–
DTBenchEpoch AI Benchmarking Hub90.9%–
ForecastBenchForecastBench63.8%†–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub73.8%†–
Show all 180 benchmarks
MetricPublisherGPT-5.2 (xhigh)MiMo-V2.6-Pro
Coding
SciCodeSciCode–60.9%
WeirdMLWeirdML72.2%–
GSO-BenchGSO-Bench27.4%†–
Arena CodingArena (LMArena)1515†1538
Arena WebDevArena (LMArena)1421†1625
LiveBench 2.0 CodingLiveBench–64.5%†
LiveBench 1.0 CodingLiveBench76.1%†–
LiveCodeBenchVals AI85.4%–
IOIVals AI–39.3%
SWE-bench (Vals)Vals AI75.8%–
SWE-Bench ProScale AI SEAL29.9%†–
SWE-bench Verified (bash only)SWE-bench69.0%†–
SWE-bench Multilingual (bash only)SWE-bench66.7%†–
SWE-bench Verified (any scaffold)SWE-bench72.8%†–
Code MigrationVals AI–43.0%
Code Migration v1.1Vals AI–48.8%
ProgramBenchVals AI–0.5%
SWE-bench MultimodalVals AI–41.3%
Vibe Code Bench v1.1Vals AI53.5%85.2%
Vibe Code Bench 1-100 v1.1Vals AI–26.4%
SWE-Bench Pro (private)Scale AI SEAL23.8%†–
MirrorCodeEpoch AI Benchmarking Hub32.2%–
ALE-BenchEpoch AI Benchmarking Hub1249.8†1158.1
AlgoTuneAlgoTune2.0†–
WeirdML v3WeirdML5.0%–
Terminal-Bench 4.0 (AA)Artificial Analysis–34.9%
GameBench 2 by reasoning settingDuelLab GameBench 2–49.8†
Design Arena WebsiteDesign Arena11861311
FrontierCode 1.1 (AA)Artificial Analysis–45.4%
FrontierCode 2.0 (AA)Artificial Analysis–24.0%
LiveCodeBench (AA)Artificial Analysis88.9%–
Agents & tools
Terminal-BenchTerminal-Bench64.9%†27.0%†
GDPvalOpenAI49.7%†–
Remote Labor IndexScale AI / CAIS2.1%†–
APEX-AgentsMercor–54.4%
Arena AgentArena (LMArena)–2.4
LiveBench Long AgenticLiveBench–36.4%†
LiveBench BrowserLiveBench–77.3%†
LiveBench Agentic CodingLiveBench50.3%†–
Terminal-Bench HardArtificial Analysis47.0%–
τ²-Bench Telecom (AA)Artificial Analysis84.8%–
Terminal-Bench 2.1 (Vals)Vals AI–67.8%
MCP AtlasScale AI SEAL67.6%–
BFCL OverallBerkeley Function Calling Leaderboard55.9%†–
τ²-benchτ²-bench84.8%†–
τ³-bench Bankingτ²-bench32.2%†–
GDPval-AA v2.1, normalised scoreArtificial Analysis–59.1%
GDPval-AA v2.1Artificial Analysis–1692
τ³-Banking (AA)Artificial Analysis11.1%†–
Analyst Agent (AA)Artificial Analysis–37.5%
CyberBenchVals AI–72.9%
Finance Agent v2Vals AI–57.3%
Finance Agent v2.1Vals AI–64.3%
Harvey's Legal Agent Benchmark v1.1Vals AI–13.8%
Harvey's Legal Agent Benchmark v1Vals AI–10.8%
Legal Research BenchVals AI–47.1%
Poker AgentVals AI1131.8%†–
SREBenchVals AI–3.0%
Tax Agent BenchVals AI–32.4%
Terminal-Bench 2.0 (Vals)Vals AI51.7%†–
Terminal-Bench 4.0 (Vals)Vals AI–31.3%
Terminal-Bench ScienceVals AI–2.9%
Arena SearchArena (LMArena)1161†–
Arena Agent Task CompletionArena (LMArena)–5
DeepResearch BenchDeepResearch Bench41.1%†–
METR Time HorizonsMETR75.3%†–
Vending-Bench 2Andon Labs3591.3†–
AutomationBenchArtificial Analysis–58.6%
GDP.pdf (AA)Artificial Analysis–19.2%
AA-Briefcase v1.1Artificial Analysis–1512
Design Arena AgenticDesign Arena1065†1271
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–5.7%
CWE-Bench (AA)Artificial Analysis–63.3%
DeepSec-Bench (AA)Artificial Analysis–26.2%
CyberGym end-to-end (AA)Artificial Analysis–78.6%
MKA (AA)Artificial Analysis–37.3%
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub67.4%–
FrontierMath Tier 4Epoch AI Benchmarking Hub31.7%–
OTIS Mock AIMEEpoch AI Benchmarking Hub96.1%–
ProofBenchVals AI15.0%70.0%
LiveBench MathematicsLiveBench93.2%†–
AIME (Vals)Vals AI96.9%–
MGSMVals AI94.0%–
AIME 2026MathArena98.3%†–
HMMT February 2026MathArena97.0%†–
MathArena ApexMathArena13.5%†–
Arena MathsArena (LMArena)1453†1484
AIME 2025 (AA)Artificial Analysis99.0%–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub37.1%–
LiveBench 2.0 Data AnalysisLiveBench–72.3%†
LiveBench ResearchLiveBench–84.8%†
LiveBench 1.0 Data AnalysisLiveBench78.2%†–
AA-Omniscience v1.1Artificial Analysis–-4.5
MMLU-ProVals AI86.2%–
LegalBenchVals AI82.8%–
CorpFinVals AI65.9%–
TaxEvalVals AI75.8%–
MedQAVals AI94.1%–
MultiNRCScale AI SEAL42.2%†–
CaseLaw v2Vals AI66.0%–
Excel Modeling BenchmarkVals AI–62.9%
Excel Modeling Benchmark v1.1Vals AI–67.3%
MedCodeVals AI49.8%45.0%
MedScribeVals AI84.4%88.3%
Public Benefits Bench v1.1Vals AI–68.9%
Access to Justice BenchmarkVals AI–70.0%
Financial Coaching BenchVals AI–75.4%
Immigration BenchVals AI–67.5%
DrugDiscoveryBenchScale AI SEAL29.3%–
EBR-benchEpoch AI Benchmarking Hub23.0%–
AA-Omniscience v1.1: accuracyArtificial Analysis–34.8%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–39.8%
Global-MMLU-Lite (AA)Artificial Analysis89.8%†–
Instruction following
LiveBench LanguageLiveBench79.8%†–
LiveBench Instruction FollowingLiveBench61.8%†–
IFBenchArtificial Analysis75.4%–
TutorBenchScale AI SEAL53.5%†–
Arena Instruction FollowingArena (LMArena)1457†1472
Human preference
Arena TextArena (LMArena)1476†1480
EQ-Bench Creative Writing v3EQ-Bench1703†–
Arena Creative WritingArena (LMArena)1432†1448
Arena Multi-turnArena (LMArena)1495†1462
Arena Longer QueriesArena (LMArena)1472†1496
Multimodal
Arena VisionArena (LMArena)1268†1266
LiveBench DesignLiveBench–74.3%†
MMMU-ProArtificial Analysis74.6%†–
VISTAScale AI SEAL46.6%†–
MMMU-Pro (Vals)Vals AI86.7%–
MortgageTaxVals AI67.1%–
SAGEVals AI–84.5%
Humanity's Sixth SenseScale AI SEAL–25.2%†
VPCTEpoch AI Benchmarking Hub84.0%–
Furniture AssemblyEpoch AI Benchmarking Hub38.3%–
VIALS-AAHandshake AI–43.5%
Code2Video-AAArtificial Analysis–1052
AA-3DArtificial Analysis–983
Long context
AA-LCR v1.1Artificial Analysis82.7%86.3%
Arena DocumentArena (LMArena)1425†–
MLCRArtificial Analysis–12.8%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub154.5†–
LiveBench 2.0LiveBench–66.1%†
LiveBench 1.0LiveBench74.6%†–
AA Intelligence Index v5.0.1Artificial Analysis–29.9
AA Intelligence Index v4.3.2Artificial Analysis30.446.3
AA Progress Index v1Artificial Analysis295.5321.2
Vals IndexVals AI–57.8
Vals Finance IndexVals AI–57.9%
Vals RSI IndexVals AI15.8%–
Vals Router IndexVals AI–57.8%
Vals Legal IndexVals AI–72.1%
AA Cyber IndexArtificial Analysis–56.1
Safety & honesty
FORTRESSScale AI SEAL17.5%†–
MASKScale AI SEAL86.7%†–
PropensityBenchScale AI SEAL34.4%†–
Metadata
AA Openness IndexArtificial Analysis–52.8

Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • MiMo-V2.6-Pro: 1 score revision.
  • GPT-5.2 (xhigh): 1 new result (AIME 2025 (AA)).
  • MiMo-V2.6-Pro: 1 score revision.
  • GPT-5.2 (xhigh): 1 new result (MirrorCode).
  • MiMo-V2.6-Pro: 6 score revisions.
  • MiMo-V2.6-Pro: 1 score revision.
  • MiMo-V2.6-Pro: 1 score revision.
  • MiMo-V2.6-Pro: BenchLeader Index 61.1 → 57.2.
  • GPT-5.2 (xhigh): 1 new result (AA Progress Index v1).
  • MiMo-V2.6-Pro: 5 new results (AA Intelligence Index v5.0.1, AA Progress Index v1, HLE-Diamond (AA)…); 3 score revisions; MiMo-V2.6-Pro cost per task moved from $0.13/M to $0.26/M (93% up).

Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs

GPT-5.2 vs MiMo-V2.6-Pro: questions

Is GPT-5.2 better than MiMo-V2.6-Pro?
GPT-5.2 (xhigh) and MiMo-V2.6-Pro are neck and neck on quality (59.9 vs 57.5, within the ±5.7 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
GPT-5.2 vs MiMo-V2.6-Pro: which is cheaper, and will that change?
MiMo-V2.6-Pro is cheaper today: $0.544 against $4.81 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is GPT-5.2 or MiMo-V2.6-Pro better for coding?
GPT-5.2 scores higher in coding (63 vs 59 on the category index, where 50 is average).
Which is faster, GPT-5.2 or MiMo-V2.6-Pro?
GPT-5.2 streams faster (76 vs 54 output tokens per second, Artificial Analysis 7-day median).
Is GPT-5.2 or MiMo-V2.6-Pro better for agents and tool use?
MiMo-V2.6-Pro scores higher in agentic tasks (57 vs 54 on the category index, where 50 is average).
More questions (4)
Which is better for long documents?
MiMo-V2.6-Pro scores higher on long-context benchmarks (68 vs 66). MiMo-V2.6-Pro accepts more context: 1,048,576 against 400,000 tokens for GPT-5.2.
Which has lower latency?
MiMo-V2.6-Pro answers first: 42.3 s against 112.5 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
Do independent benchmarks agree on GPT-5.2 vs MiMo-V2.6-Pro?
Across the 9 benchmarks both have, GPT-5.2 leads 1, MiMo-V2.6-Pro leads 8. Every overall index that rates both puts MiMo-V2.6-Pro ahead.
When was MiMo-V2.6-Pro released?
MiMo-V2.6-Pro was released on 21 Sep 2026.