VECTOR WIREAI INTELLIGENCE
UTC
Refresh Models Deals Regulatory Sources

MiMo V2.6 Flash RL vs Claude Opus 5

8 SHARED BENCHMARKS

Across 8 shared benchmarks, MiMo V2.6 Flash RL scores higher on 1 and Claude Opus 5 on 7. The widest gap is Program Bench, where Claude Opus 5 scores 85.4 against 26. MiMo V2.6 Flash RL is the cheaper of the two on tracked API pricing ($0.14 against $5.00 per million input tokens).

XIAOMIVSANTHROPIC8 SHARED17 HEAD-TO-HEADNEWEST SCORE ADDED

At a glance

MakerXiaomiAnthropic
Released
Price per 1M tokens input / output$0.14 / $0.28$5.00 / $25.00
Cost of 1M in + 1M out$0.42 71.4× less$30.00
Head-to-head of 8 shared benchmarks1 wins7 wins
Scores tracked independently verified9 0194 22

Release dates: the Hugging Face repository date for MiMo V2.6 Flash RL; the vendor's own announcement for Claude Opus 5. Prices: deepinfra for MiMo V2.6 Flash RL; Anthropic's own price page for Claude Opus 5. ◆ = independently verified score.

Where each leadsby capability area · benchmark wins

AreaMiMo V2.6 Flash RLWINSClaude Opus 5
Coding10MiMo V2.6 Flash RL leads 1 of 1
Agentic01Claude Opus 5 leads 1 of 1

Every shared benchmark8 · grouped by area

Agentic 1

Other shared benchmarks 6

DeepSWE 1.167.968.8
JobBench61.265.7
Terminal-Bench 4.028.852.3

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 (deepinfra, anthropic-official), otherwise the lowest tracked offer.

Compare Claude Opus 5 withALL PAIRINGS →