VECTOR WIREAI INTELLIGENCE
UTC
Refresh Models Deals Regulatory Sources

MiMo V2.6 Pro vs Claude Opus 5

19 SHARED BENCHMARKS

Across 19 shared benchmarks, MiMo V2.6 Pro scores higher on 8 and Claude Opus 5 on 10, with 1 level. The widest gap is AA-Omniscience, where Claude Opus 5 scores 31 against 8.4. MiMo V2.6 Pro is the cheaper of the two on tracked API pricing ($0.43 against $5.00 per million input tokens).

XIAOMIVSANTHROPIC19 SHARED810 HEAD-TO-HEADNEWEST SCORE ADDED

At a glance

MakerXiaomiAnthropic
Released
Price per 1M tokens input / output$0.43 / $0.87$5.00 / $25.00
Cost of 1M in + 1M out$1.30 23.1× less$30.00
Head-to-head of 19 shared benchmarks8 wins10 wins
Scores tracked independently verified21 1198 22

Release dates: Artificial Analysis for MiMo V2.6 Pro; the vendor's own announcement for Claude Opus 5. Prices: Artificial Analysis for MiMo V2.6 Pro; Artificial Analysis for Claude Opus 5. ◆ = independently verified score.

Where each leadsby capability area · benchmark wins

AreaMiMo V2.6 ProWINSClaude Opus 5
Reasoning02Claude Opus 5 leads 2 of 2
Coding20MiMo V2.6 Pro leads 2 of 2 · widest: SciCode 60.9 vs 51.5
Agentic21MiMo V2.6 Pro leads 2 of 3 · widest: GDPVal 58.7 vs 48.8
Factuality11Even, 1–1 of 2
Long Context10MiMo V2.6 Pro leads 1 of 1 · widest: AA-LCR 86.3 vs 82

Biggest gaps

MiMo V2.6 Pro pulls furthest ahead on

  1. AA-Omniscience · Non-hallucination59.4 vs 39.3
  2. GDPVal58.7 vs 48.8
  3. SciCode60.9 vs 51.5

Claude Opus 5 pulls furthest ahead on

  1. AA-Omniscience · Accuracy57.1 vs 34.9

Every shared benchmark19 · grouped by area

Reasoning 2

Coding 2

Agentic 3

GDPVal58.748.8
Terminal-Bench 4.034.834.3

Long Context 1

Other shared benchmarks 9

DeepSWE 1.171.968.8
GDPval-AA 2.116731708
JobBench6265.7
Terminal-Bench 4.034.942

Each score is the one the model's own page shows — the most authoritative tracked result for that benchmark, on the benchmark's standard methodology (source-attributed). ↓ marks lower-is-better metrics; ◆ an independently verified score. Open either model for its full surface, provenance and pricing. Quoted rates are the price-setter row we currently track for each model — its direct or vendor-official listing where one exists (direct, direct), otherwise the lowest tracked offer.

Compare Claude Opus 5 withALL PAIRINGS →