Llama 3.1 Instruct 405B vs Qwen3.5 35B A3B
Wins 1 of 6 areas
Facts
Wins 5 of 6 areas
Coding · Agents · Reasoning · Long documents · Following instructions
Qwen3.5 35B A3B is the stronger all-rounder.Llama 3.1 Instruct 405B is better at facts.
Scores updated · 32 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 software04Qwen3.5 35B A3B4 of 4 tests
- ReasoningHard problems that need careful thinking02Qwen3.5 35B A3B2 of 3 tests · 1 tie
- Long documentsFinding answers in very long texts02Qwen3.5 35B A3B2 of 2 tests
- AgentsCarrying out multi-step tasks on its own01Qwen3.5 35B A3B1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3.5 35B A3B1 of 1 test
- FactsGetting facts right instead of making them up20Llama 3.1 Instruct 405B2 of 2 tests
Agents 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Qwen3.5 35B A3B pulls ahead
- Reasons across sets of long documentsAA-LCR+46.7points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+44.7points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+33.5points ahead
Where Llama 3.1 Instruct 405B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+33points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+3.1points ahead
Every test, side by side
All 32 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.5 35B A3B
- SWE-bench VerifiedQwen3.5 35B A3B by 44.724.569.2+44.7
- SWE-bench ProQwen3.5 35B A3B by 33.411.244.6+33.4
- Terminal-Bench HardQwen3.5 35B A3B by 19.76.826.5+19.7
- SciCodeQwen3.5 35B A3B by 7.829.937.7+7.8
ReasoningQwen3.5 35B A3B
- GPQA DiamondQwen3.5 35B A3B by 3351.584.5+33
- Humanity's Last ExamQwen3.5 35B A3B by 17421+17
- CritPttie00.9tie
FactsLlama 3.1 Instruct 405B
- AA-Omniscience · Non-hallucinationLlama 3.1 Instruct 405B by 3347.614.6+33
- AA-Omniscience · AccuracyLlama 3.1 Instruct 405B by 3.123.220.1+3.1
Long documentsQwen3.5 35B A3B
- AA-LCRQwen3.5 35B A3B by 46.725.372+46.7
- LongBench v2Qwen3.5 35B A3B by 22.936.159+22.9
Following instructionsQwen3.5 35B A3B
- IFBenchQwen3.5 35B A3B by 33.53972.5+33.5
Other results19 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.
- τ²-Bench Telecom (AA run)Qwen3.5 35B A3B by 70.21989.2+70.2
- OpenBookQALlama 3.1 Instruct 405B by 49.89444.2+49.8
- AA-OmniscienceLlama 3.1 Instruct 405B by 31-17.1-48.1+31
- Artificial Analysis Coding IndexQwen3.5 35B A3B by 22.514.537+22.5
- HumanEvalLlama 3.1 Instruct 405B by 22.58966.5+22.5
- BFCLv4Llama 3.1 Instruct 405B by 21.288.567.3+21.2
- C-EvalQwen3.5 35B A3B by 17.772.590.2+17.7
- AA IntelligenceQwen3.5 35B A3B by 127.319.3+12
- MMLU-ProQwen3.5 35B A3B by 1273.385.3+12
- MMMLUQwen3.5 35B A3B by 11.473.885.2+11.4
- MMLULlama 3.1 Instruct 405B by 7.588.681.1+7.5
- MMLU-ReduxQwen3.5 35B A3B by 7.186.293.3+7.1
- WinoGrandeLlama 3.1 Instruct 405B by 685.279.2+6
- AA Agentic IndexQwen3.5 35B A3B by 5.56.311.8+5.5
- HellaSwagLlama 3.1 Instruct 405B by 3.689.285.6+3.6
- PIQA (Acc.)Llama 3.1 Instruct 405B by 3.685.982.3+3.6
- IFEvalQwen3.5 35B A3B by 3.388.691.9+3.3
- MBPPQwen3.5 35B A3B by 2.468.470.8+2.4
- ARC-ChallengeLlama 3.1 Instruct 405B by 1.596.995.4+1.5
Questions people ask
Which is better, Llama 3.1 Instruct 405B or Qwen3.5 35B A3B?
Qwen3.5 35B A3B wins five of the six areas where both have results: coding, agents, reasoning, long documents and following instructions. Llama 3.1 Instruct 405B wins facts.
Which is better for coding?
Qwen3.5 35B A3B. It wins 4 of the 4 coding tests both models report; Llama 3.1 Instruct 405B wins none.
How do you compare the two?
We use the 32 benchmark tests both models have published scores on. The verdict counts the 13 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 19 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.