Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models816Deals30d269Policy30d79, 18 pendingSources1,157

MiMo V2.6 Pro vs Qwen3.8 Max Preview

Xiaomi · released

Wins 3 of 6 areas

Coding · Reasoning · Long documents

Alibaba · released

Wins 2 of 6 areas

Agents · Images and charts

MiMo V2.6 Pro wins more areas, narrowly.Qwen3.8 Max Preview is better at agents.

Both rank among the ten best models we track in long documents.

Scores updated · 19 tests both models report · How we compare

Where each one wins

Tests won in each of the six areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.

Images and charts and long documents rest on a single test each.

What it costs

Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.

MiMo V2.6 Pro$0.43 to read · $0.87 to write$1.30Price from Artificial Analysis
Qwen3.8 Max Preview$2.00 to read · $6.00 to write$8.00Price from Artificial Analysis

MiMo V2.6 Pro costs 84% less for the same work.

The biggest differences

The three tests each model wins by the widest margin. Scores are out of 100.

Where MiMo V2.6 Pro pulls ahead

  • Research-level physics problemsCritPt+8.9points aheadMiMo V2.6 Pro26.6Qwen3.8 Max Preview17.7
  • Code for real scientific research problemsSciCode+8.8points aheadMiMo V2.6 Pro60.9Qwen3.8 Max Preview52.1
  • Very hard expert questions across many subjectsHumanity's Last Exam+6.3points aheadMiMo V2.6 Pro49.4Qwen3.8 Max Preview43.1

Where Qwen3.8 Max Preview pulls ahead

  • Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+11.8points aheadQwen3.8 Max Preview71.2MiMo V2.6 Pro59.4
  • Completes tasks by operating a computer desktopOSWorld-Verified+4.1points aheadQwen3.8 Max Preview86.1MiMo V2.6 Pro82
  • Complex command-line tasks across many fieldsTerminal-Bench 4.0+4.1points aheadQwen3.8 Max Preview38.9MiMo V2.6 Pro34.8

Every test, side by side

All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingMiMo V2.6 Pro

Full coding ranking

AgentsQwen3.8 Max Preview
  • OSWorld-VerifiedQwen3.8 Max Preview by 4.18286.1+4.1
  • Terminal-Bench 4.0Qwen3.8 Max Preview by 4.134.838.9+4.1
  • GDPValtie59.258.3tie

Full agents ranking

ReasoningMiMo V2.6 Pro

Full reasoning ranking

FactsEven

Full facts ranking

Images and chartsQwen3.8 Max Preview

Full images and charts ranking

Long documentsMiMo V2.6 Pro
  • AA-LCRMiMo V2.6 Pro by 686.380.3+6

Full long documents ranking

Other results7 tests, not counted

Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.

Questions people ask

Which is better, MiMo V2.6 Pro or Qwen3.8 Max Preview?

MiMo V2.6 Pro wins three of the six areas where both have results: coding, reasoning and long documents. Qwen3.8 Max Preview wins agents and images and charts. They are level on facts.

Which is better for coding?

MiMo V2.6 Pro. It wins 2 of the 3 coding tests both models report; Qwen3.8 Max Preview wins 1.

Which is cheaper?

MiMo V2.6 Pro costs $0.43 per million input tokens and $0.87 per million output tokens; Qwen3.8 Max Preview costs $2.00 and $6.00. That makes MiMo V2.6 Pro about 84% cheaper for the same work.

How do you compare the two?

We use the 19 benchmark tests both models have published scores on. The verdict counts the 12 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 7 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.