Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d66, 14 pendingSources1,015

Qwen3.5 122B A10B vs Qwen3.5 4B

Alibaba · released

Wins 7 of 7 areas

Coding · Agents · Reasoning · Facts · Images and charts · Long documents · Following instructions

Alibaba · released

Wins 0 of 7 areas

—

Qwen3.5 122B A10B is the stronger all-rounder.Qwen3.5 4B is cheaper.

Scores updated · 41 tests both models report · How we compare

Where each one wins

Tests won in each of the seven 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.

Agents rests on a single test.

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.

Qwen3.5 122B A10B$0.40 to read · $3.20 to write$3.60Price from Alibaba's own price page
Qwen3.5 4B$0.03 to read · $0.15 to write$0.18Price from Artificial Analysis

Qwen3.5 4B costs 95% less for the same work.

The biggest differences

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

Where Qwen3.5 122B A10B pulls ahead

  • Math problems shown in pictures and chartsMathVista+23.8points aheadQwen3.5 122B A10B87.4Qwen3.5 4B63.6
  • Follows unfamiliar, precisely checkable instructionsIFBench+23.7points aheadQwen3.5 122B A10B75.7Qwen3.5 4B52
  • Code for real scientific research problemsSciCode+23.6points aheadQwen3.5 122B A10B39.7Qwen3.5 4B16.1

Where Qwen3.5 4B pulls ahead

No clear win on a test scored out of 100.

Every test, side by side

All 41 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingQwen3.5 122B A10B

Full coding ranking

AgentsQwen3.5 122B A10B

Full agents ranking

ReasoningQwen3.5 122B A10B

Full reasoning ranking

FactsQwen3.5 122B A10B

Full facts ranking

Images and chartsQwen3.5 122B A10B
  • MathVistaQwen3.5 122B A10B by 23.887.463.6+23.8
  • MMStarQwen3.5 122B A10B by 23.682.959.3+23.6
  • MMMUQwen3.5 122B A10B by 10.583.973.4+10.5
  • MMMU-ProQwen3.5 122B A10B by 9.67565.4+9.6
  • OCRBenchQwen3.5 122B A10B by 5.292.186.9+5.2

Full images and charts ranking

Long documentsQwen3.5 122B A10B
  • AA-LCRQwen3.5 122B A10B by 13.376.363+13.3
  • LongBench v2Qwen3.5 122B A10B by 10.260.250+10.2

Full long documents ranking

Following instructionsQwen3.5 122B A10B

Full following instructions ranking

Other results22 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, Qwen3.5 122B A10B or Qwen3.5 4B?

Qwen3.5 122B A10B wins all seven areas where both have results: coding, agents, reasoning, facts, images and charts, long documents and following instructions. Qwen3.5 4B wins none, but costs 95% less.

Which is better for coding?

Qwen3.5 122B A10B. It wins 4 of the 4 coding tests both models report; Qwen3.5 4B wins none.

Which is cheaper?

Qwen3.5 122B A10B costs $0.40 per million input tokens and $3.20 per million output tokens; Qwen3.5 4B costs $0.03 and $0.15. That makes Qwen3.5 4B about 95% cheaper for the same work.

How do you compare the two?

We use the 41 benchmark tests both models have published scores on. The verdict counts the 19 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 22 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.

Compare Qwen3.5 4B with

Alibaba

Across the field

All comparisons