GPT-4o vs Qwen3 Next 80B A3B Instruct
Wins 2 of 6 areas
Facts · Long documents
Wins 3 of 6 areas
Agents · Reasoning · Following instructions
Qwen3 Next 80B A3B Instruct wins more areas, narrowly.GPT-4o is better at facts.
Scores updated · 27 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.
- ReasoningHard problems that need careful thinking02Qwen3 Next 80B A3B Instruct2 of 3 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own01Qwen3 Next 80B A3B Instruct1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3 Next 80B A3B Instruct1 of 1 test
- FactsGetting facts right instead of making them up20GPT-4o2 of 2 tests
- Long documentsFinding answers in very long texts10GPT-4o1 of 1 test
- CodingWriting and fixing software11Even1 each · 1 tie
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 Next 80B A3B Instruct costs 93% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Qwen3 Next 80B A3B Instruct pulls ahead
- Recent programming contest problemsLiveCodeBench v6+25.7points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+21.2points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+5.8points ahead
Where GPT-4o pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+54.8points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+6.4points ahead
- Reasons across sets of long documentsAA-LCR+3.3points ahead
Every test, side by side
All 27 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- LiveCodeBench v6Qwen3 Next 80B A3B Instruct by 25.730.956.6+25.7
- SciCodeGPT-4o by 2.633.330.7+2.6
- Terminal-Bench Hardtie8.37.6tie
AgentsQwen3 Next 80B A3B Instruct
- GDPValQwen3 Next 80B A3B Instruct by 6.406.4+6.4
ReasoningQwen3 Next 80B A3B Instruct
- GPQA DiamondQwen3 Next 80B A3B Instruct by 21.252.673.8+21.2
- Humanity's Last ExamQwen3 Next 80B A3B Instruct by 5.81.87.6+5.8
- CritPttie00tie
FactsGPT-4o
- AA-Omniscience · Non-hallucinationGPT-4o by 54.862.17.3+54.8
- AA-Omniscience · AccuracyGPT-4o by 6.423.717.3+6.4
Following instructionsQwen3 Next 80B A3B Instruct
- IFBenchQwen3 Next 80B A3B Instruct by 3.73639.7+3.7
Other results16 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.
- AIME 2025Qwen3 Next 80B A3B Instruct by 57.811.769.5+57.8
- AA-OmniscienceGPT-4o by 49-10.5-59.5+49
- Aider-PolyglotQwen3 Next 80B A3B Instruct by 19.130.749.8+19.1
- SuperGPQAQwen3 Next 80B A3B Instruct by 16.442.458.8+16.4
- MMLU-ProXQwen3 Next 80B A3B Instruct by 15.661.176.7+15.6
- Artificial Analysis Coding IndexGPT-4o by 8.924.215.3+8.9
- τ²-Bench Telecom (AA run)GPT-4o by 7.328.921.6+7.3
- IFEvalQwen3 Next 80B A3B Instruct by 6.68187.6+6.6
- τ²-Bench (Retail)GPT-4o by 6.163.457.3+6.1
- MMLU-ProQwen3 Next 80B A3B Instruct by 5.974.780.6+5.9
- AA Agentic IndexQwen3 Next 80B A3B Instruct by 5.88.414.2+5.8
- MMLU-ReduxQwen3 Next 80B A3B Instruct by 2.98890.9+2.9
- AA IntelligenceQwen3 Next 80B A3B Instruct by 2.37.39.6+2.3
- TAU-bench (airline)Qwen3 Next 80B A3B Instruct by 1.242.844+1.2
- TAU-bench (retail)tie60.360.9tie
- Tau2 airlinetie45.545.5tie
Questions people ask
Which is better, GPT-4o or Qwen3 Next 80B A3B Instruct?
Qwen3 Next 80B A3B Instruct wins three of the six areas where both have results: agents, reasoning and following instructions. GPT-4o wins facts and long documents. 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-4o costs $5.00 per million input tokens and $15.00 per million output tokens; Qwen3 Next 80B A3B Instruct costs $0.15 and $1.20. That makes Qwen3 Next 80B A3B Instruct about 93% cheaper for the same work.
How do you compare the two?
We use the 27 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 16 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.