Qwen3 Next 80B A3B Instruct vs Qwen3 VL 30B A3B Instruct
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents · Following instructions
Wins 0 of 6 areas
—
Qwen3 Next 80B A3B Instruct is the stronger all-rounder.Qwen3 VL 30B A3B Instruct is cheaper.
Scores updated · 26 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.
- CodingWriting and fixing software20Qwen3 Next 80B A3B Instruct2 of 3 tests · 1 tie
- ReasoningHard problems that need careful thinking20Qwen3 Next 80B A3B Instruct2 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up20Qwen3 Next 80B A3B Instruct2 of 2 tests
- AgentsCarrying out multi-step tasks on its own10Qwen3 Next 80B A3B Instruct1 of 1 test
- Long documentsFinding answers in very long texts10Qwen3 Next 80B A3B Instruct1 of 1 test
- Following instructionsDoing exactly what it is asked10Qwen3 Next 80B A3B Instruct1 of 1 test
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.
Qwen3 VL 30B A3B Instruct costs 26% 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 Next 80B A3B Instruct pulls ahead
- Reasons across sets of long documentsAA-LCR+25.4points ahead
- Recent programming contest problemsLiveCodeBench v6+14points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+6.6points ahead
Where Qwen3 VL 30B A3B Instruct pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 26 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3 Next 80B A3B Instruct
- LiveCodeBench v6Qwen3 Next 80B A3B Instruct by 1456.642.6+14
- Terminal-Bench HardQwen3 Next 80B A3B Instruct by 1.57.66.1+1.5
- SciCodetie30.730.8tie
AgentsQwen3 Next 80B A3B Instruct
- GDPValQwen3 Next 80B A3B Instruct by 6.46.40+6.4
ReasoningQwen3 Next 80B A3B Instruct
- GPQA DiamondQwen3 Next 80B A3B Instruct by 4.373.869.5+4.3
- Humanity's Last ExamQwen3 Next 80B A3B Instruct by 1.37.66.3+1.3
- CritPttie00tie
FactsQwen3 Next 80B A3B Instruct
- AA-Omniscience · AccuracyQwen3 Next 80B A3B Instruct by 1.717.315.6+1.7
- AA-Omniscience · Non-hallucinationQwen3 Next 80B A3B Instruct by 17.36.3+1
Long documentsQwen3 Next 80B A3B Instruct
- AA-LCRQwen3 Next 80B A3B Instruct by 25.452.727.3+25.4
Following instructionsQwen3 Next 80B A3B Instruct
- IFBenchQwen3 Next 80B A3B Instruct by 6.639.733.1+6.6
Other results15 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.
- Arena-Hard-V2Qwen3 Next 80B A3B Instruct by 24.282.758.5+24.2
- IncludeQwen3 Next 80B A3B Instruct by 7.378.971.6+7.3
- MMLU-ProXQwen3 Next 80B A3B Instruct by 5.876.770.9+5.8
- SuperGPQAQwen3 Next 80B A3B Instruct by 5.758.853.1+5.7
- AA Agentic IndexQwen3 Next 80B A3B Instruct by 4.714.29.5+4.7
- BFCL v3Qwen3 Next 80B A3B Instruct by 470.366.3+4
- AA-OmniscienceQwen3 Next 80B A3B Instruct by 3.9-59.5-63.4+3.9
- HMMT 2025Qwen3 Next 80B A3B Instruct by 3.554.150.6+3.5
- MMLU-ProQwen3 Next 80B A3B Instruct by 2.880.677.8+2.8
- τ²-Bench Telecom (AA run)Qwen3 Next 80B A3B Instruct by 2.621.619+2.6
- MMLU-ReduxQwen3 Next 80B A3B Instruct by 2.590.988.4+2.5
- IFEvalQwen3 Next 80B A3B Instruct by 1.887.685.8+1.8
- AA IntelligenceQwen3 Next 80B A3B Instruct by 1.79.67.9+1.7
- Artificial Analysis Coding IndexQwen3 Next 80B A3B Instruct by 115.314.3+1
- AIME 2025tie69.569.3tie
Questions people ask
Which is better, Qwen3 Next 80B A3B Instruct or Qwen3 VL 30B A3B Instruct?
Qwen3 Next 80B A3B Instruct wins all six areas where both have results: coding, agents, reasoning, facts, long documents and following instructions. Qwen3 VL 30B A3B Instruct wins none, but costs 26% less.
Which is better for coding?
Qwen3 Next 80B A3B Instruct. It wins 2 of the 3 coding tests both models report; Qwen3 VL 30B A3B Instruct wins none, and 1 is a tie.
Which is cheaper?
Qwen3 Next 80B A3B Instruct costs $0.15 per million input tokens and $1.20 per million output tokens; Qwen3 VL 30B A3B Instruct costs $0.20 and $0.80. That makes Qwen3 VL 30B A3B Instruct about 26% cheaper for the same work.
How do you compare the two?
We use the 26 benchmark tests both models have published scores on. The verdict counts the 11 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.