GenMagic logoGenMagic
Sign in

Claude Sonnet 4.6 vs MiMo-V2.6-Pro

Anthropic against Xiaomi. Prices, scores and speed below are live.

  • MiMo-V2.6-Pro costs 91% less on blended price ($0.82 against $9.00 per 1M tokens, 3 input to 1 output).
  • Claude Sonnet 4.6 scores higher on the Artificial Analysis Intelligence Index: 30.5 against 29.9.
  • On the 22 benchmarks both have scores on, Claude Sonnet 4.6 leads on 1 and MiMo-V2.6-Pro on 21.
  • MiMo-V2.6-Pro reads more context: 1.1M tokens against 1M.
  • MiMo-V2.6-Pro is newer: listed Sep 21, 2026, against Feb 17, 2026.
Run both on your promptClaude Sonnet 4.6MiMo-V2.6-Pro

Side by side

Claude Sonnet 4.6MiMo-V2.6-Pro
LabAnthropicXiaomi
ListedFeb 17, 2026Sep 21, 2026
Input per 1M tokens$4.50$0.65
Output per 1M tokens$22.50$1.30
Cached input per 1M$0.45$0.0054
Blended (3:1) per 1M$9.00$0.82
Context window1M1.1M
Max output128K131K
Knowledge cutoff--
Intelligence index30.529.9
Coding index63-
ReasoningYesYes
Reads imagesYesYes
Tool useYesYes
Structured outputYesYes

Every benchmark both are scored on

Each model's best score per benchmark, with its source. Scores from different sources or settings are not always comparable; each links to where it was published.

BenchmarkClaude Sonnet 4.6MiMo-V2.6-Pro
APEX-Agents43%Epoch AI54.4%Epoch AI
Artificial Analysis Intelligence Index30.5Artificial Analysis and OpenRouter29.9Artificial Analysis and OpenRouter
Design Arena: 3D1231 EloDesign Arena1333 EloDesign Arena
Design Arena: Code1274 EloDesign Arena1315 EloDesign Arena
Design Arena: Data Viz1278 EloDesign Arena1337 EloDesign Arena
Design Arena: Game Dev1259 EloDesign Arena1315 EloDesign Arena
Design Arena: SVG1193 EloDesign Arena1305 EloDesign Arena
Design Arena: UI Component1266 EloDesign Arena1336 EloDesign Arena
Design Arena: Web Apps (agentic)1175 EloDesign Arena1275 EloDesign Arena
Design Arena: Website1283 EloDesign Arena1307 EloDesign Arena
GPQA Diamond69.3%Artificial Analysis and OpenRouter88.8%Artificial Analysis and OpenRouter
LMArena (Coding)1503 EloLMArena1534 EloLMArena
LMArena (Overall)1458 EloLMArena1491 EloLMArena
LMArena: Creative Writing1435 EloLMArena1464 EloLMArena
LMArena: Hard Prompts1484 EloLMArena1511 EloLMArena
LMArena: Longer Query1479 EloLMArena1502 EloLMArena
LMArena: Math1483 EloLMArena1513 EloLMArena
LMArena: Multi-Turn1463 EloLMArena1466 EloLMArena
ProofBench45%Epoch AI70%Epoch AI
SciCode46.8%Epoch AI60.9%Epoch AI
tau-bench (Airline)74.3%Artificial Analysis and OpenRouter76.8%Artificial Analysis and OpenRouter
WebDev Arena1521 EloEpoch AI1618 EloEpoch AI

More comparisons

Where these figures come from

Prices are GenMagic's own, what the studio and the API charge, recomputed from each provider's price list every few minutes. The indices are the Artificial Analysis indices, and every benchmark score links to its source, re-read daily. Measured speed is GenMagic's own generation records, in aggregate. See Anthropic models, Xiaomi models, every LLM's price and our sources.