Claude Sonnet 4.5 vs Qwen3 Next 80B A3B
Wins 5 of 6 areas
Coding · Agents · Reasoning · Facts · Long documents
Wins 1 of 6 areas
Following instructions
Claude Sonnet 4.5 is the stronger all-rounder.Qwen3 Next 80B A3B is cheaper and better at following instructions.
Scores updated · 35 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 thinking30Claude Sonnet 4.53 of 3 tests
- CodingWriting and fixing software31Claude Sonnet 4.53 of 4 tests
- AgentsCarrying out multi-step tasks on its own20Claude Sonnet 4.52 of 2 tests
- FactsGetting facts right instead of making them up21Claude Sonnet 4.52 of 3 tests
- Long documentsFinding answers in very long texts10Claude Sonnet 4.51 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3 Next 80B A3B1 of 1 test
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 costs 93% 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 Claude Sonnet 4.5 pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+49.1points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+37.9points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+25.8points ahead
Where Qwen3 Next 80B A3B pulls ahead
- Recent programming contest problemsLiveCodeBench v6+4.7points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+3.4points ahead
Every test, side by side
All 35 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4.5
- Terminal-Bench 2.1Claude Sonnet 4.5 by 49.155.86.7+49.1
- Terminal-Bench HardClaude Sonnet 4.5 by 25.835.69.8+25.8
- SciCodeClaude Sonnet 4.5 by 6.945.738.8+6.9
- LiveCodeBench v6Qwen3 Next 80B A3B by 4.76468.7+4.7
AgentsClaude Sonnet 4.5
- GDPValClaude Sonnet 4.5 by 20.520.50+20.5
- τ-Bench V3 · BankingClaude Sonnet 4.5 by 18.324.56.2+18.3
ReasoningClaude Sonnet 4.5
- GPQA DiamondClaude Sonnet 4.5 by 7.583.475.9+7.5
- Humanity's Last ExamClaude Sonnet 4.5 by 5.217.812.6+5.2
- CritPtClaude Sonnet 4.5 by 1.11.10+1.1
FactsClaude Sonnet 4.5
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.5 by 37.950.913+37.9
- AA-Omniscience · AccuracyClaude Sonnet 4.5 by 13.932.919+13.9
- Vectara HHEM hallucination ratelower is betterQwen3 Next 80B A3B by 2.7129.3+2.7
Long documentsClaude Sonnet 4.5
- AA-LCRClaude Sonnet 4.5 by 8.672.363.7+8.6
Following instructionsQwen3 Next 80B A3B
- IFBenchQwen3 Next 80B A3B by 3.457.360.7+3.4
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.
- AA-OmniscienceClaude Sonnet 4.5 by 51.3-0.1-51.4+51.3
- τ²-Bench Telecom (AA run)Claude Sonnet 4.5 by 36.678.141.5+36.6
- Artificial Analysis Coding IndexClaude Sonnet 4.5 by 34.752.117.4+34.7
- TAU-bench (airline)Claude Sonnet 4.5 by 217049+21
- τ²-Bench (Retail)Claude Sonnet 4.5 by 18.486.267.8+18.4
- TAU-bench (retail)Claude Sonnet 4.5 by 16.686.269.6+16.6
- AA Agentic IndexClaude Sonnet 4.5 by 15.417.52.1+15.4
- AA IntelligenceClaude Sonnet 4.5 by 9.520.711.2+9.5
- HarmBenchClaude Sonnet 4.5 by 7.49284.6+7.4
- bbqClaude Sonnet 4.5 by 7.298.991.7+7.2
- vectara_avg_summary_lengthClaude Sonnet 4.5 by 56.9 rating points127.870.9+56.9 rating
- MMLU-ProClaude Sonnet 4.5 by 4.887.582.7+4.8
- AIR-Bench 2024Claude Sonnet 4.5 by 3.189.886.7+3.1
- MMLU-ReduxClaude Sonnet 4.5 by 3.195.692.5+3.1
- vectara_factual_consistencyQwen3 Next 80B A3B by 2.78890.7+2.7
- XSTestQwen3 Next 80B A3B by 1.996.498.3+1.9
- anthropic_red_teamQwen3 Next 80B A3B by 1.798.299.9+1.7
- vectara_answer_rateClaude Sonnet 4.5 by 1.295.694.4+1.2
- AIME 2025tie8787.8tie
- HMMT 2025tie74.673.9tie
- simple_safety_teststie10099.5tie
Questions people ask
Which is better, Claude Sonnet 4.5 or Qwen3 Next 80B A3B?
Claude Sonnet 4.5 wins five of the six areas where both have results: coding, agents, reasoning, facts and long documents. Qwen3 Next 80B A3B wins following instructions, and costs 93% less.
Which is better for coding?
Claude Sonnet 4.5. It wins 3 of the 4 coding tests both models report; Qwen3 Next 80B A3B wins 1.
Which is cheaper?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; Qwen3 Next 80B A3B costs $0.15 and $1.20. That makes Qwen3 Next 80B A3B about 93% cheaper for the same work.
How do you compare the two?
We use the 35 benchmark tests both models have published scores on. The verdict counts the 14 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.