VECTOR WIREAI INTELLIGENCE
UTC
Refresh Models Deals Regulatory Sources

GPT-5.5 vs MiMo V2.6 Pro

18 SHARED BENCHMARKS

Across 18 shared benchmarks, GPT-5.5 scores higher on 3 and MiMo V2.6 Pro on 15. The widest gap is AA-Omniscience · Non-hallucination, where MiMo V2.6 Pro scores 59.4 against 12. MiMo V2.6 Pro is the cheaper of the two on tracked API pricing ($0.43 against $5.00 per million input tokens).

OPENAIVSXIAOMI18 SHARED315 HEAD-TO-HEADNEWEST SCORE ADDED

At a glance

MakerOpenAIXiaomi
Released
Price per 1M tokens input / output$5.00 / $30.00$0.43 / $0.87
Cost of 1M in + 1M out$35.00$1.30 26.9× less
Head-to-head of 18 shared benchmarks3 wins15 wins
Scores tracked independently verified204 3521 1

Release dates per Artificial Analysis. Prices: Artificial Analysis for GPT-5.5; Artificial Analysis for MiMo V2.6 Pro. ◆ = independently verified score.

Where each leadsby capability area · benchmark wins

AreaGPT-5.5WINSMiMo V2.6 Pro
Reasoning02MiMo V2.6 Pro leads 2 of 2 · widest: Humanity's Last Exam 45 vs 49.4
Coding02MiMo V2.6 Pro leads 2 of 2 · widest: Terminal-Bench 2.1 79.4 vs 89.9
Agentic03MiMo V2.6 Pro leads 3 of 3 · widest: Terminal-Bench 4.0 9.1 vs 34.8
Factuality11Even, 1–1 of 2
Long Context01MiMo V2.6 Pro leads 1 of 1

Biggest gaps

GPT-5.5 pulls furthest ahead on

  1. AA-Omniscience · Accuracy57 vs 34.9

MiMo V2.6 Pro pulls furthest ahead on

  1. AA-Omniscience · Non-hallucination59.4 vs 12
  2. Terminal-Bench 4.034.8 vs 9.1
  3. GDPVal58.7 vs 40.5

Every shared benchmark18 · grouped by area

Reasoning 2

Coding 2

BenchmarkGPT-5.5MARGINMiMo V2.6 Pro
SciCode56.160.9

Agentic 3

BenchmarkGPT-5.5MARGINMiMo V2.6 Pro
GDPVal40.558.7
Terminal-Bench 4.09.134.8

Long Context 1

BenchmarkGPT-5.5MARGINMiMo V2.6 Pro
AA-LCR84.386.3

Other shared benchmarks 8

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 GPT-5.5 withALL PAIRINGS →