o3 vs Qwen3.5 397B A17B
Wins 2 of 8 areas
Facts · Math
Wins 6 of 8 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
Qwen3.5 397B A17B is the stronger all-rounder.o3 is better at facts.
Scores updated · 27 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. 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
- Images and chartsUnderstanding pictures, charts and video03Qwen3.5 397B A17B3 of 3 tests
- ReasoningHard problems that need careful thinking02Qwen3.5 397B A17B2 of 3 tests · 1 tie
- 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
- FactsGetting facts right instead of making them up20o32 of 3 tests · 1 tie
- MathCompetition and research-level math10o31 of 1 test
Math 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.
Qwen3.5 397B A17B costs 58% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Qwen3.5 397B A17B pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+19.3points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+8.9points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+7.4points ahead
Where o3 pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+23.4points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+7.8points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+2.1points ahead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.
CodingQwen3.5 397B A17B
- SWE-bench VerifiedQwen3.5 397B A17B by 7.369.176.4+7.3
- SciCodeQwen3.5 397B A17B by 3.84144.8+3.8
- Terminal-Bench HardQwen3.5 397B A17B by 3.837.140.9+3.8
AgentsQwen3.5 397B A17B
- BrowseCompQwen3.5 397B A17B by 19.349.769+19.3
- GDPValQwen3.5 397B A17B by 212.814.8+2
ReasoningQwen3.5 397B A17B
- Humanity's Last ExamQwen3.5 397B A17B by 8.920.129+8.9
- GPQA DiamondQwen3.5 397B A17B by 6.682.789.3+6.6
- CritPttie1.11.7tie
Factso3
- SimpleQA Verifiedo3 by 23.449.426+23.4
- AA-Omniscience · Accuracyo3 by 7.838.630.8+7.8
- AA-Omniscience · Non-hallucinationtie11.911.1tie
Images and chartsQwen3.5 397B A17B
- MMMU-ProQwen3.5 397B A17B by 7.270.177.3+7.2
- LMArena · VisionQwen3.5 397B A17B by 50 rating points12141264+50 rating
- MMMUQwen3.5 397B A17B by 2.182.985+2.1
Long documentsQwen3.5 397B A17B
- LongBench v2Qwen3.5 397B A17B by 4.458.863.2+4.4
- AA-LCRQwen3.5 397B A17B by 2.674.777.3+2.6
Following instructionsQwen3.5 397B A17B
- IFBenchQwen3.5 397B A17B by 7.471.478.8+7.4
- Multi-ChallengeQwen3.5 397B A17B by 7.260.467.6+7.2
Other results8 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 Agentic Indexo3 by 25.536.110.6+25.5
- HMMT Feb. 2025Qwen3.5 397B A17B by 17.377.594.8+17.3
- AA-Omniscienceo3 by 15.2-15.6-30.8+15.2
- τ²-Bench Telecom (AA run)Qwen3.5 397B A17B by 14.980.795.6+14.9
- Artificial Analysis Coding IndexQwen3.5 397B A17B by 9.838.448.2+9.8
- MMLU-ProQwen3.5 397B A17B by 2.88587.8+2.8
- StrongREJECTQwen3.5 397B A17B by 2.49799.4+2.4
- AA Intelligenceo3 by 1.820.218.4+1.8
Questions people ask
Which is better, o3 or Qwen3.5 397B A17B?
Qwen3.5 397B A17B wins six of the eight areas we test: coding, agents, reasoning, images and charts, long documents and following instructions. o3 wins facts and math.
Which is better for coding?
Qwen3.5 397B A17B. It wins 3 of the 3 coding tests both models report; o3 wins none.
Which is cheaper?
o3 costs $2.00 per million input tokens and $8.00 per million output tokens; Qwen3.5 397B A17B costs $0.60 and $3.60. That makes Qwen3.5 397B A17B about 58% 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 19 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 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.