BenchLeader

GPT-6 Astra vs MiMo-V2.6-Pro

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

Updated · Data from 13 sources

As of 16 Nov 2026, GPT-6 Astra is ahead of MiMo-V2.6-Pro on quality (67.3 vs 57.5 on the BenchLeader Index), but MiMo-V2.6-Pro is 37× cheaper at $0.544 vs $20.00 per 1M tokens blended. Choose GPT-6 Astra for knowledge (72 vs 42), reasoning (72 vs 50), and coding (73 vs 59); choose MiMo-V2.6-Pro for fast first answers (42.3 s vs 198.4 s) and long context (68 vs 65), where it also streams faster.

Key facts (as of 16 Nov 2026)

  • GPT-6 Astra scores 67.3 on the BenchLeader Index and MiMo-V2.6-Pro scores 57.5 (BenchLeader, 16 Nov 2026).
  • GPT-6 Astra costs $20.00 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).
  • MiMo-V2.6-Pro streams faster than GPT-6 Astra (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 70 benchmarks both models have, GPT-6 Astra leads 48 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, GPT-6 Astra is rated 1764 and MiMo-V2.6-Pro 1625 (LMArena, as published by 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-6 Astra73 vs 59 category score; Arena WebDev 1764 vs 1625High
Agents & tool useGPT-6 Astra64 vs 57 category score; Arena Agent 14.5 vs 2.4Medium
MathsGPT-6 Astra71 vs 66 category score; Arena Maths 1481 vs 1484Medium
ReasoningGPT-6 Astra72 vs 50 category score; HLE-Diamond (AA) 63.8% vs 15.2%High
KnowledgeGPT-6 Astra72 vs 42 category score; AA-Omniscience v1.1 42.4 vs -4.5High
Long documentsMiMo-V2.6-Pro68 vs 65 category score; AA-LCR v1.1 86.3% vs 80.7%Medium
Images and other mediaGPT-6 Astra66 vs 60 category score; Arena Vision 1279 vs 1266Medium
Chat quality (human preference)Either66 vs 67 on Arena votesEither
Lowest costMiMo-V2.6-Pro$0.548 vs $20.00 per 1M blended; agentic coding session $0.030 vs $0.800–
Fastest first answerMiMo-V2.6-Pro42.3 s (MiMo-V2.6-Pro) vs 198.4 s (GPT-6 Astra (max)) 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-6 Astra (max) leads on quality: 67.3 vs 57.5.
  • GPT-6 Astra (max) is stronger in agents & tools, coding, knowledge, maths, multimodal, reasoning.
  • MiMo-V2.6-Pro is stronger in human preference, long context.
  • MiMo-V2.6-Pro is 37× cheaper ($0.544 vs $20.00 per 1M blended).
  • MiMo-V2.6-Pro streams 1.3× faster (54 vs 41 tokens per second).

At a glance

SpecGPT-6 AstraMiMo-V2.6-Pro
DeveloperOpenAIXiaomi
Released2 Sep 202621 Sep 2026
Context window (tokens)1,050,0001,048,576
Compared atGPT-6 Astra (max)MiMo-V2.6-Pro
Open weightsNoYes
Price in / out / cached input per 1M$10.00 / $50.00 / $1.00$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-6 Astra (max)MiMo-V2.6-ProLeader
Reasoning72.449.9GPT-6 Astra
Coding73.258.8GPT-6 Astra
Agents & tools63.957.1GPT-6 Astra
Maths70.865.5GPT-6 Astra
Knowledge72.342.3GPT-6 Astra
Human preference66.267.0level
Multimodal65.660.2GPT-6 Astra
Long context65.067.9MiMo-V2.6-Pro
Composite71.3–not comparable

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 contextMultimodalHumanpreferenceGPT-6 Astra, Reasoning: 72.4GPT-6 Astra, Coding: 73.2GPT-6 Astra, Agents & tools: 63.9GPT-6 Astra, Maths: 70.8GPT-6 Astra, Knowledge: 72.3GPT-6 Astra, Long context: 65.0GPT-6 Astra, Multimodal: 65.6GPT-6 Astra, Human preference: 66.2MiMo-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: 67.9MiMo-V2.6-Pro, Multimodal: 60.2MiMo-V2.6-Pro, Human preference: 67.0

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

Model, click to add or removeIndex

Where sources disagree

Across the 70 benchmarks both have, GPT-6 Astra leads 48, MiMo-V2.6-Pro leads 21 and 1 is a tie. Independent sources split: GPT-6 Astra leads on BenchLeader Index, AA Intelligence Index v5.0.1 and Vals Index; MiMo-V2.6-Pro leads on Arena Text.

Overall indexGPT-6 Astra (max)MiMo-V2.6-ProLeader
BenchLeader Index67.357.5GPT-6 Astra
AA Intelligence Index v5.0.156.929.9GPT-6 Astra
Vals Index65.057.8GPT-6 Astra
Arena Text14741480MiMo-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-6 Astra (max)MiMo-V2.6-Pro
Blended price per 1M tokens$20.00$0.548
Input / output per 1M$10.00 / $50.00$0.440 / $0.870
Cached input per 1M$1.00$0.0036
Price per task: chat reply$0.019$0.0004
Price per task: summarize a 30-page report$0.150$0.0058
Price per task: code edit$0.135$0.0039
Price per task: agentic coding session$0.800$0.030
Price per task: structured extraction$0.030$0.0011
Agentic coding session, input mostly cached$0.395$0.010
Cost per benchmark task (AA Index)$6.24$0.257
Output tokens per task (AA Index)52k121k
Of which reasoning36k86k
Time per task (AA Index)21 min38 min
Output speed41 tok/s54 tok/s
Time to first answer198.4 s42.3 s
Time to a complete answer, last measured 13 Nov 2026533.7 s95.7 s

Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $6.24 on GPT-6 Astra (max) and $0.257 on MiMo-V2.6-Pro, and MiMo-V2.6-Pro wrote 2.3× as many output tokens for the same work, which a per-token price hides.

Each model is compared at its best-ranked reasoning-effort setting. GPT-6 Astra (max) scores 67.3 and takes 198 s to its first answer token; GPT-6 Astra scores 66.4 in 5 s, GPT-6 Astra (high) scores 66.3 in 49 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

176 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-6 Astra (max)MiMo-V2.6-Pro
BenchLeader IndexBenchLeader67.357.5
Agents & tools scoreBenchLeader63.957.1
Coding scoreBenchLeader73.258.8
Composite scoreBenchLeader71.3–
Human preference scoreBenchLeader66.267.0
Knowledge scoreBenchLeader72.342.3
Long context scoreBenchLeader65.067.9
Maths scoreBenchLeader70.865.5
Multimodal scoreBenchLeader65.660.2
Reasoning scoreBenchLeader72.449.9
Blended price $/MBenchLeader$20.00$0.548
Output speedBenchLeader41 tok/s54 tok/s
Time to first answerBenchLeader198.4 s42.3 s
Context windowBenchLeader1,050,000 tokens1,048,576 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub95.8%–
Humanity's Last ExamScale AI / CAIS54.8%†–
SimpleBenchSimpleBench83.6%†–
Arena Hard PromptsArena (LMArena)15001504
LiveBench 2.0 ReasoningLiveBench92.7%79.6%†
LiveBench 1.0 ReasoningLiveBench92.7%–
GPQA Diamond (AA)Artificial Analysis96.1%–
Humanity's Last Exam (AA)Artificial Analysis54.7%49.4%
HLE-Diamond (AA)Artificial Analysis63.8%15.2%
ARC-AGI-1ARC Prize97.5%–
ARC-AGI-2ARC Prize95.0%–
ARC-AGI-3ARC Prize98.6%–
CritPtArtificial Analysis31.7%26.6%
CritPt v2 hard subset (AA)Artificial Analysis70.5%34.0%
MysteryMechanismVals AI53.1%15.3%
HLE-Diamond (Scale)Scale AI SEAL60.6%†–
Arena ExpertArena (LMArena)15171526
Chess PuzzlesEpoch AI Benchmarking Hub74.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub84.0%–
LMCAEpoch AI Benchmarking Hub64.1%†–
DTBenchEpoch AI Benchmarking Hub97.1%†–
ForecastBenchForecastBench66.6%†–
BTF-3Epoch AI Benchmarking Hub13.5%†–
Coding
SciCodeSciCode56.5%60.9%
WeirdMLWeirdML93.3%–
Show all 176 benchmarks
MetricPublisherGPT-6 Astra (max)MiMo-V2.6-Pro
Coding
FrontierCodeCognition53.3%–
GSO-BenchGSO-Bench79.4%†–
Arena CodingArena (LMArena)15481538
Arena WebDevArena (LMArena)17641625
LiveBench 2.0 CodingLiveBench87.5%64.5%†
LiveBench 1.0 CodingLiveBench80.4%–
IOIVals AI100.0%39.3%
Code MigrationVals AI67.7%43.0%
Code Migration v1.1Vals AI80.6%48.8%
ProgramBenchVals AI5.5%0.5%
SWE-bench MultimodalVals AI43.3%41.3%
Vibe Code Bench 1-100Vals AI27.6%–
Vibe Code Bench v1.1Vals AI89.6%85.2%
Vibe Code Bench 1-100 v1.1Vals AI–26.4%
SWE Atlas v1.0: Codebase QnAScale AI SEAL59.1%†–
SWE Atlas v1.0: RefactoringScale AI SEAL59.0%†–
SWE Atlas v1.0: Test WritingScale AI SEAL50.7%†–
SWE Atlas v1.1Scale AI SEAL69.4%†–
SWE Atlas v1.1: Codebase QnAScale AI SEAL70.2%†–
SWE Atlas v1.1: Test WritingScale AI SEAL66.7%†–
SWE Atlas v1.1: RefactoringScale AI SEAL71.4%†–
SWE-Bench Pro V2Scale AI SEAL96.9%†–
SWE-Bench Pro V2 HARDScale AI SEAL90.2%†–
MirrorCodeEpoch AI Benchmarking Hub60.0%–
DeepSWE v1.1Epoch AI Benchmarking Hub73.2%–
ALE-BenchEpoch AI Benchmarking Hub2951.31158.1
FrontierSWEEpoch AI Benchmarking Hub65.5%–
WeirdML v3WeirdML42.2%†–
Terminal-Bench 4.0 (AA)Artificial Analysis59.1%34.9%
Terminal-Bench 2.1 (AA)Artificial Analysis88.4%–
Startrise FrontendStartrise79.9%†–
GameBench 2 OverallDuelLab GameBench 288.8†–
GameBench 2 by reasoning settingDuelLab GameBench 294.3†49.8†
Design Arena WebsiteDesign Arena13381311
FrontierCode 1.1 (AA)Artificial Analysis47.0%45.4%
FrontierCode 2.0 (AA)Artificial Analysis42.4%24.0%
Agents & tools
Terminal-BenchTerminal-Bench60.3%27.0%†
Remote Labor IndexScale AI / CAIS20.8%†–
APEX-AgentsMercor64.7%†54.4%
Arena AgentArena (LMArena)14.52.4
LiveBench Long AgenticLiveBench75.6%36.4%†
LiveBench BrowserLiveBench91.3%77.3%†
LiveBench Agentic CodingLiveBench57.3%–
Terminal-Bench 2.1 (Vals)Vals AI87.3%67.8%
HiL-BenchScale AI SEAL65.3%†–
GDPval-AA v2.1, normalised scoreArtificial Analysis53.7%59.1%
GDPval-AA v2.1Artificial Analysis15871692
τ³-Banking (AA)Artificial Analysis41.4%–
ITBench SRE (AA)Artificial Analysis48.6%–
Analyst Agent (AA)Artificial Analysis51.3%37.5%
CUA-benchVals AI19.2%–
CyberBenchVals AI41.1%72.9%
Finance Agent v2Vals AI53.5%57.3%
Finance Agent v2.1Vals AI60.4%64.3%
Harvey's Legal Agent Benchmark v1.1Vals AI7.1%13.8%
Harvey's Legal Agent Benchmark v1Vals AI5.4%10.8%
Legal Research BenchVals AI39.4%47.1%
Robo-benchVals AI23.3%–
SREBenchVals AI56.9%3.0%
Tax Agent BenchVals AI20.7%32.4%
Terminal-Bench 4.0 (Vals)Vals AI59.6%31.3%
Terminal-Bench ScienceVals AI62.9%2.9%
Time Horizon Index: KSPVals AI90.5%–
Arena SearchArena (LMArena)1245–
Arena Agent Task CompletionArena (LMArena)145
BALROGBALROG68.3%–
PostTrainBenchEpoch AI Benchmarking Hub41.9%–
Vending-Bench 2Andon Labs15514.7†–
SpireClimbEpoch AI Benchmarking Hub34.0%–
AutomationBenchArtificial Analysis68.5%58.6%
GDP.pdf (AA)Artificial Analysis31.0%19.2%
Harvey LAB-AA v1.1Harvey8.6%–
AA-Briefcase v1.1Artificial Analysis15691512
GDPxGDPx by SemiAnalysis9.6%–
Design Arena AgenticDesign Arena14051271
RoboDojo (LLM as robot policy)RoboDojo29.0†–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis63.3%5.7%
CWE-Bench (AA)Artificial Analysis63.3%63.3%
DeepSec-Bench (AA)Artificial Analysis36.9%26.2%
CyberGym end-to-end (AA)Artificial Analysis0.0%78.6%
MKA (AA)Artificial Analysis50.2%37.3%
FACTS SearchGoogle93.3%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub93.7%–
FrontierMath Tier 4Epoch AI Benchmarking Hub97.6%–
OTIS Mock AIMEEpoch AI Benchmarking Hub100.0%–
ProofBenchVals AI99.0%†70.0%
LiveBench MathematicsLiveBench96.8%–
Arena MathsArena (LMArena)14811484
FrontierMath ErdősEpoch AI Benchmarking Hub2.9%–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub75.6%–
LiveBench 2.0 Data AnalysisLiveBench83.0%72.3%†
LiveBench ResearchLiveBench90.6%84.8%†
LiveBench 1.0 Data AnalysisLiveBench83.0%–
AA-Omniscience v1.1Artificial Analysis42.4-4.5
PRBench FinanceScale AI SEAL47.5%†–
PRBench LegalScale AI SEAL48.4%†–
BioMysteryBenchVals AI79.3%–
Excel Modeling BenchmarkVals AI71.7%62.9%
Excel Modeling Benchmark v1.1Vals AI72.7%67.3%
MedCodeVals AI48.5%45.0%
MedScribeVals AI87.9%88.3%
Public Benefits Bench v1.1Vals AI–68.9%
Access to Justice BenchmarkVals AI–70.0%
Financial Coaching BenchVals AI67.5%75.4%
Immigration BenchVals AI67.7%67.5%
DrugDiscoveryBenchScale AI SEAL68.7%–
EBR-benchEpoch AI Benchmarking Hub76.2%–
GDP.pdfEpoch AI Benchmarking Hub34.2%–
AA-Omniscience v1.1: accuracyArtificial Analysis61.6%34.8%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis50.2%39.8%
HealthBench Professional (AA)OpenAI66.0%–
FACTS ParametricGoogle83.8%†–
Instruction following
LiveBench LanguageLiveBench89.4%–
LiveBench Instruction FollowingLiveBench75.6%–
Arena Instruction FollowingArena (LMArena)14741472
Human preference
Arena TextArena (LMArena)14741480
EQ-Bench Creative Writing v3EQ-Bench2177†–
Arena Creative WritingArena (LMArena)14511448
Arena Multi-turnArena (LMArena)14831462
Arena Longer QueriesArena (LMArena)14851496
Multimodal
Arena VisionArena (LMArena)12791266
LiveBench DesignLiveBench80.0%74.3%†
MMMU-ProArtificial Analysis86.9%–
SAGEVals AI–84.5%
Humanity's Sixth SenseScale AI SEAL53.6%25.2%†
Blueprint-Bench 2Epoch AI Benchmarking Hub49.7%†–
Furniture AssemblyEpoch AI Benchmarking Hub80.0%–
VIALS-AAHandshake AI62.7%43.5%
Code2Video-AAArtificial Analysis14271052
AA-3DArtificial Analysis1168983
FACTS MultimodalGoogle55.2%†–
Long context
AA-LCR v1.1Artificial Analysis80.7%86.3%
Arena DocumentArena (LMArena)1474–
MLCRArtificial Analysis41.7%12.8%
FACTS GroundingGoogle80.1%†–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub169†–
LiveBench 2.0LiveBench84.5%66.1%†
LiveBench 1.0LiveBench82.2%–
AA Intelligence Index v5.0.1Artificial Analysis56.929.9
AA Intelligence Index v4.3.2Artificial Analysis52.746.3
AA Progress Index v1Artificial Analysis349.6321.2
Vals IndexVals AI65.057.8
Vals Finance IndexVals AI55.6%57.9%
Vals RSI IndexVals AI27.1%–
Vals Science IndexVals AI65.1%–
Vals Router IndexVals AI65.0%†57.8%
Vals Legal IndexVals AI68.4%72.1%
AA Cyber IndexArtificial Analysis33.456.1
Safety & honesty
FORTRESSScale AI SEAL12.1%†–
DistressBenchScale AI SEAL74.3%†–
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

  • GPT-6 Astra (max): 8 new results (LiveBench 2.0, LiveBench Long Agentic, LiveBench 2.0 Reasoning…).
  • MiMo-V2.6-Pro: 1 score revision.
  • GPT-6 Astra (max): 1 score revision.
  • GPT-6 Astra (max): 1 new result (PostTrainBench); 2 score revisions.
  • MiMo-V2.6-Pro: 1 score revision.
  • GPT-6 Astra (max): 1 new result (MirrorCode); 1 score revision.
  • GPT-6 Astra (max): BenchLeader Index 68.1 → 67.4.
  • GPT-6 Astra (max): 2 score revisions.
  • MiMo-V2.6-Pro: 6 score revisions.
  • GPT-6 Astra (max): 1 score revision.

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

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

Is GPT-6 Astra better than MiMo-V2.6-Pro?
GPT-6 Astra (max) leads on quality: 67.3 vs 57.5. The BenchLeader Index combines every independent quality benchmark; GPT-6 Astra (max) is ahead overall as of 16 Nov 2026, but check the category scores for your use.
GPT-6 Astra vs MiMo-V2.6-Pro: which is cheaper, and will that change?
MiMo-V2.6-Pro is cheaper today: $0.544 against $20.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is GPT-6 Astra or MiMo-V2.6-Pro better for coding?
GPT-6 Astra scores higher in coding (73 vs 59 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1764 for GPT-6 Astra against 1625 for MiMo-V2.6-Pro.
Which is faster, GPT-6 Astra or MiMo-V2.6-Pro?
MiMo-V2.6-Pro streams faster (54 vs 41 output tokens per second, Artificial Analysis 7-day median).
Is GPT-6 Astra or MiMo-V2.6-Pro better for agents and tool use?
GPT-6 Astra scores higher in agentic tasks (64 vs 57 on the category index, where 50 is average). On Arena Agent, the top shared agents & tools benchmark, it is 14.5 for GPT-6 Astra against 2.4 for MiMo-V2.6-Pro.
More questions (4)
Which is better for long documents?
MiMo-V2.6-Pro scores higher on long-context benchmarks (68 vs 65). Both take about 1.1M tokens: GPT-6 Astra 1,050,000, MiMo-V2.6-Pro 1,048,576.
Which has lower latency?
MiMo-V2.6-Pro answers first: 42.3 s against 198.4 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-6 Astra vs MiMo-V2.6-Pro?
Across the 70 benchmarks both have, GPT-6 Astra leads 48, MiMo-V2.6-Pro leads 21 and 1 is a tie. Independent sources split: GPT-6 Astra leads on BenchLeader Index, AA Intelligence Index v5.0.1 and Vals Index; MiMo-V2.6-Pro leads on Arena Text.
When was MiMo-V2.6-Pro released?
MiMo-V2.6-Pro was released on 21 Sep 2026.