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

GPT-4.1 vs Qwen3 Next 80B A3B

OpenAI · released

Wins 3 of 6 areas

Agents · Facts · Long documents

Alibaba · released

Wins 2 of 6 areas

Reasoning · Following instructions

GPT-4.1 wins more areas, narrowly.Qwen3 Next 80B A3B is cheaper and better at reasoning.

Scores updated · 33 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.

Agents, long documents and following instructions 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.

GPT-4.1$2.00 to read · $8.00 to write$10Price from Artificial Analysis
Qwen3 Next 80B A3B$0.15 to read · $1.20 to write$1.35Price from Artificial Analysis

Qwen3 Next 80B A3B costs 87% less for the same work.

The biggest differences

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

Where GPT-4.1 pulls ahead

  • Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+8.8points aheadGPT-4.127.8Qwen3 Next 80B A3B19
  • Reasons across sets of long documentsAA-LCR+4.6points aheadGPT-4.168.3Qwen3 Next 80B A3B63.7
  • Hard command-line tasks in a real terminalTerminal-Bench Hard+3.8points aheadGPT-4.113.6Qwen3 Next 80B A3B9.8

Where Qwen3 Next 80B A3B pulls ahead

  • Recent programming contest problemsLiveCodeBench v6+24points aheadQwen3 Next 80B A3B68.7GPT-4.144.7
  • Follows unfamiliar, precisely checkable instructionsIFBench+17.7points aheadQwen3 Next 80B A3B60.7GPT-4.143
  • Graduate-level biology, physics and chemistry questionsGPQA Diamond+9.3points aheadQwen3 Next 80B A3B75.9GPT-4.166.6

Every test, side by side

All 33 tests both models report. The winning score is in its model's colour; marks a score checked independently.

CodingEven

Full coding ranking

AgentsGPT-4.1
  • GDPValGPT-4.1 by 13.813.80+13.8

Full agents ranking

ReasoningQwen3 Next 80B A3B

Full reasoning ranking

FactsGPT-4.1

Full facts ranking

Long documentsGPT-4.1
  • AA-LCRGPT-4.1 by 4.668.363.7+4.6

Full long documents ranking

Following instructionsQwen3 Next 80B A3B
  • IFBenchQwen3 Next 80B A3B by 17.74360.7+17.7

Full following instructions ranking

Other results21 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, GPT-4.1 or Qwen3 Next 80B A3B?

GPT-4.1 wins three of the six areas where both have results: agents, facts and long documents. Qwen3 Next 80B A3B wins reasoning and following instructions, and costs 87% less. They are level on coding.

Which is better for coding?

Neither. They win 1 coding test each of the 3 both models report, and 1 is a tie.

Which is cheaper?

GPT-4.1 costs $2.00 per million input tokens and $8.00 per million output tokens; Qwen3 Next 80B A3B costs $0.15 and $1.20. That makes Qwen3 Next 80B A3B about 87% cheaper for the same work.

How do you compare the two?

We use the 33 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 21 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.