o4-mini vs Qwen3.5 397B A17B
Wins 1 of 8 areas
Math
Wins 6 of 8 areas
Coding · Reasoning · Facts · Images and charts · Long documents · Following instructions
Qwen3.5 397B A17B is the stronger all-rounder.o4-mini is better at math.
Scores updated · 25 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.
- ReasoningHard problems that need careful thinking03Qwen3.5 397B A17B3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video03Qwen3.5 397B A17B3 of 3 tests
- Following instructionsDoing exactly what it is asked02Qwen3.5 397B A17B2 of 2 tests
- CodingWriting and fixing software12Qwen3.5 397B A17B2 of 3 tests
- FactsGetting facts right instead of making them up12Qwen3.5 397B A17B2 of 3 tests
- Long documentsFinding answers in very long texts01Qwen3.5 397B A17B1 of 1 test
- MathCompetition and research-level math10o4-mini1 of 1 test
- AgentsCarrying out multi-step tasks on its own11Even1 each
Math and long documents 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.
Qwen3.5 397B A17B costs 24% 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
- Hard command-line tasks in a real terminalTerminal-Bench Hard+25.7points ahead
- Keeps track of context across a multi-turn chatMulti-Challenge+24.6points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+17.5points ahead
Where o4-mini pulls ahead
- Real work tasks from 44 professionsGDPVal+10.6points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+8.4points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+4.9points ahead
Every test, side by side
All 25 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.5 397B A17B
- Terminal-Bench HardQwen3.5 397B A17B by 25.715.240.9+25.7
- SWE-bench VerifiedQwen3.5 397B A17B by 8.368.176.4+8.3
- SciCodeo4-mini by 1.746.544.8+1.7
AgentsEven
- BrowseCompQwen3.5 397B A17B by 17.551.569+17.5
- GDPValo4-mini by 10.625.414.8+10.6
ReasoningQwen3.5 397B A17B
- Humanity's Last ExamQwen3.5 397B A17B by 12.516.529+12.5
- GPQA DiamondQwen3.5 397B A17B by 10.978.489.3+10.9
- CritPtQwen3.5 397B A17B by 1.10.61.7+1.1
FactsQwen3.5 397B A17B
- AA-Omniscience · Non-hallucinationo4-mini by 8.419.511.1+8.4
- SimpleQA VerifiedQwen3.5 397B A17B by 7.218.826+7.2
- AA-Omniscience · AccuracyQwen3.5 397B A17B by 624.830.8+6
Images and chartsQwen3.5 397B A17B
- MMMU-ProQwen3.5 397B A17B by 8.169.277.3+8.1
- LMArena · VisionQwen3.5 397B A17B by 70 rating points11941264+70 rating
- MMMUQwen3.5 397B A17B by 3.481.685+3.4
Long documentsQwen3.5 397B A17B
- AA-LCRQwen3.5 397B A17B by 16.36177.3+16.3
Following instructionsQwen3.5 397B A17B
- Multi-ChallengeQwen3.5 397B A17B by 24.64367.6+24.6
- IFBenchQwen3.5 397B A17B by 10.168.778.8+10.1
Other results7 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 397B A17B by 4055.695.6+40
- AA Agentic Indexo4-mini by 25.536.110.6+25.5
- Artificial Analysis Coding IndexQwen3.5 397B A17B by 22.625.648.2+22.6
- MMLU-ProXQwen3.5 397B A17B by 15.469.384.7+15.4
- AA-OmniscienceQwen3.5 397B A17B by 5-35.7-30.8+5
- StrongREJECTQwen3.5 397B A17B by 3.49699.4+3.4
- AA IntelligenceQwen3.5 397B A17B by 1.716.718.4+1.7
Questions people ask
Which is better, o4-mini or Qwen3.5 397B A17B?
Qwen3.5 397B A17B wins six of the eight areas we test: coding, reasoning, facts, images and charts, long documents and following instructions. o4-mini wins math. They are level on agents.
Which is better for coding?
Qwen3.5 397B A17B. It wins 2 of the 3 coding tests both models report; o4-mini wins 1.
Which is cheaper?
o4-mini costs $1.10 per million input tokens and $4.40 per million output tokens; Qwen3.5 397B A17B costs $0.60 and $3.60. That makes Qwen3.5 397B A17B about 24% cheaper for the same work.
How do you compare the two?
We use the 25 benchmark tests both models have published scores on. The verdict counts the 18 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 7 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.