Qwen3.7 Plus Preview vs Qwen3.8 Max Preview
Wins 0 of 8 areas
—
Wins 7 of 8 areas
Coding · Agents · Reasoning · Images and charts · Math · Long documents · Following instructions
Qwen3.8 Max Preview is the stronger all-rounder.Qwen3.7 Plus Preview is cheaper.
Scores updated · 36 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.
- AgentsCarrying out multi-step tasks on its own05Qwen3.8 Max Preview5 of 5 tests
- CodingWriting and fixing software03Qwen3.8 Max Preview3 of 3 tests
- ReasoningHard problems that need careful thinking03Qwen3.8 Max Preview3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video02Qwen3.8 Max Preview2 of 2 tests
- MathCompetition and research-level math01Qwen3.8 Max Preview1 of 1 test
- Long documentsFinding answers in very long texts01Qwen3.8 Max Preview1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3.8 Max Preview1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Math, 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.
Qwen3.7 Plus Preview costs 75% 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 Qwen3.8 Max Preview pulls ahead
- Real work tasks from 44 professionsGDPVal+44.9points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+40.3points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+37.9points ahead
Where Qwen3.7 Plus Preview pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+1.1points ahead
Every test, side by side
All 36 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.8 Max Preview
- Terminal-Bench 2.1Qwen3.8 Max Preview by 27.86188.8+27.8
- SWE-bench ProQwen3.8 Max Preview by 10.157.667.7+10.1
- SciCodeQwen3.8 Max Preview by 646.152.1+6
AgentsQwen3.8 Max Preview
- GDPValQwen3.8 Max Preview by 44.913.458.3+44.9
- Terminal-Bench 4.0Qwen3.8 Max Preview by 37.9138.9+37.9
- τ-Bench V3 · BankingQwen3.8 Max Preview by 30.317.547.8+30.3
- AA ApexAgentsQwen3.8 Max Preview by 2022.442.4+20
- OSWorld-VerifiedQwen3.8 Max Preview by 12.873.386.1+12.8
ReasoningQwen3.8 Max Preview
- CritPtQwen3.8 Max Preview by 8.69.117.7+8.6
- Humanity's Last ExamQwen3.8 Max Preview by 7.535.643.1+7.5
- GPQA DiamondQwen3.8 Max Preview by 2.89092.8+2.8
FactsEven
- AA-Omniscience · AccuracyQwen3.8 Max Preview by 9.222.531.7+9.2
- AA-Omniscience · Non-hallucinationQwen3.7 Plus Preview by 1.172.371.2+1.1
Images and chartsQwen3.8 Max Preview
- LMArena · VisionQwen3.8 Max Preview by 35 rating points12771312+35 rating
- MMMU-ProQwen3.8 Max Preview by 2.380.582.8+2.3
MathQwen3.8 Max Preview
- FrontierMath Tiers 1-3 (v2)Qwen3.8 Max Preview by 40.334.474.7+40.3
Long documentsQwen3.8 Max Preview
- AA-LCRQwen3.8 Max Preview by 7.37380.3+7.3
Following instructionsQwen3.8 Max Preview
- IFBenchQwen3.8 Max Preview by 4.87882.8+4.8
Other results18 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-briefcaseQwen3.8 Max Preview by 690.6 rating points915.41606+690.6 rating
- DeepSWE 1.1Qwen3.8 Max Preview by 40.116.556.6+40.1
- Agents' Last ExamQwen3.8 Max Preview by 39.213.252.4+39.2
- AA Agentic IndexQwen3.8 Max Preview by 29.919.749.6+29.9
- JobBenchQwen3.8 Max Preview by 25.827.653.4+25.8
- Toolathlon VerifiedQwen3.8 Max Preview by 21.950.672.5+21.9
- AA IntelligenceQwen3.8 Max Preview by 20.225.245.4+20.2
- Artificial Analysis Coding IndexQwen3.8 Max Preview by 15.955.971.8+15.9
- NL2RepoQwen3.8 Max Preview by 14.841.155.9+14.8
- AA-OmniscienceQwen3.8 Max Preview by 10.91.112+10.9
- GDP (Surge AI)Qwen3.8 Max Preview by 10.612.222.8+10.6
- HLE-DiamondQwen3.8 Max Preview by 10.113.924+10.1
- ERQAQwen3.8 Max Preview by 869.877.8+8
- enterprise-ops-gym-aaQwen3.8 Max Preview by 740.647.6+7
- LVBenchQwen3.8 Max Preview by 5.676.281.8+5.6
- ScreenSpot-Pro (No tools)Qwen3.8 Max Preview by 5.57984.5+5.5
- AndroidWorldQwen3.8 Max Preview by 4.38185.3+4.3
- RealWorldQAQwen3.8 Max Preview by 1.186.988+1.1
Questions people ask
Which is better, Qwen3.7 Plus Preview or Qwen3.8 Max Preview?
Qwen3.8 Max Preview wins seven of the eight areas we test: coding, agents, reasoning, images and charts, math, long documents and following instructions. Qwen3.7 Plus Preview wins none, but costs 75% less. They are level on facts.
Which is better for coding?
Qwen3.8 Max Preview. It wins 3 of the 3 coding tests both models report; Qwen3.7 Plus Preview wins none.
Which is cheaper?
Qwen3.7 Plus Preview costs $0.40 per million input tokens and $1.60 per million output tokens; Qwen3.8 Max Preview costs $2.00 and $6.00. That makes Qwen3.7 Plus Preview about 75% cheaper for the same work.
How do you compare the two?
We use the 36 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 18 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.