Qwen3.5 0.8B vs Qwen3.5 397B A17B
Wins 0 of 7 areas
—
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
Qwen3.5 397B A17B is the stronger all-rounder.
Scores updated · 30 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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 software03Qwen3.5 397B A17B3 of 3 tests
- ReasoningHard problems that need careful thinking03Qwen3.5 397B A17B3 of 3 tests
- AgentsCarrying out multi-step tasks on its own02Qwen3.5 397B A17B2 of 2 tests
- Long documentsFinding answers in very long texts02Qwen3.5 397B A17B2 of 2 tests
- Following instructionsDoing exactly what it is asked02Qwen3.5 397B A17B2 of 2 tests
- Images and chartsUnderstanding pictures, charts and video01Qwen3.5 397B A17B1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Images and charts rests on a single test.
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 397B A17B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+78.2points ahead
- Reasons across sets of long documentsAA-LCR+68.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+57.3points ahead
Where Qwen3.5 0.8B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+27.6points ahead
Every test, side by side
All 30 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.5 397B A17B
- Terminal-Bench 2.1Qwen3.5 397B A17B by 51.3051.3+51.3
- SciCodeQwen3.5 397B A17B by 44.8044.8+44.8
- Terminal-Bench HardQwen3.5 397B A17B by 40.9040.9+40.9
AgentsQwen3.5 397B A17B
- GDPValQwen3.5 397B A17B by 14.8014.8+14.8
- τ-Bench V3 · BankingQwen3.5 397B A17B by 13.4013.4+13.4
ReasoningQwen3.5 397B A17B
- GPQA DiamondQwen3.5 397B A17B by 78.211.189.3+78.2
- Humanity's Last ExamQwen3.5 397B A17B by 27.91.129+27.9
- CritPtQwen3.5 397B A17B by 1.701.7+1.7
FactsEven
- AA-Omniscience · Non-hallucinationQwen3.5 0.8B by 27.638.711.1+27.6
- AA-Omniscience · AccuracyQwen3.5 397B A17B by 26.64.230.8+26.6
Images and chartsQwen3.5 397B A17B
- MMMU-ProQwen3.5 397B A17B by 51.525.877.3+51.5
Long documentsQwen3.5 397B A17B
- AA-LCRQwen3.5 397B A17B by 68.3977.3+68.3
- LongBench v2Qwen3.5 397B A17B by 37.126.163.2+37.1
Following instructionsQwen3.5 397B A17B
- IFBenchQwen3.5 397B A17B by 57.321.578.8+57.3
- Multi-ChallengeQwen3.5 397B A17B by 48.718.967.6+48.7
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.
- t2-benchQwen3.5 397B A17B by 75.111.686.7+75.1
- MMLU-ProXQwen3.5 397B A17B by 50.134.684.7+50.1
- SuperGPQAQwen3.5 397B A17B by 49.121.370.4+49.1
- Artificial Analysis Coding IndexQwen3.5 397B A17B by 48.2048.2+48.2
- τ²-Bench Telecom (AA run)Qwen3.5 397B A17B by 47.947.795.6+47.9
- BFCLv4Qwen3.5 397B A17B by 47.625.372.9+47.6
- MMLU-ProQwen3.5 397B A17B by 45.542.387.8+45.5
- IncludeQwen3.5 397B A17B by 4540.685.6+45
- MMMLUQwen3.5 397B A17B by 44.244.388.5+44.2
- C-EvalQwen3.5 397B A17B by 42.550.593+42.5
- MMLU-ReduxQwen3.5 397B A17B by 35.459.594.9+35.4
- AA-OmniscienceQwen3.5 397B A17B by 23.8-54.5-30.8+23.8
- IFEvalQwen3.5 397B A17B by 21.471.292.6+21.4
- AA IntelligenceQwen3.5 397B A17B by 12.36.118.4+12.3
- AA Agentic IndexQwen3.5 397B A17B by 4.95.710.6+4.9
Questions people ask
Which is better, Qwen3.5 0.8B or Qwen3.5 397B A17B?
Qwen3.5 397B A17B wins six of the seven areas where both have results: coding, agents, reasoning, images and charts, long documents and following instructions. Qwen3.5 0.8B wins none. They are level on facts.
Which is better for coding?
Qwen3.5 397B A17B. It wins 3 of the 3 coding tests both models report; Qwen3.5 0.8B wins none.
How do you compare the two?
We use the 30 benchmark tests both models have published scores on. The verdict counts the 15 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.