Gemini 3.1 Pro vs Qwen3.8 Max Preview
Wins 3 of 8 areas
Reasoning · Facts · Long documents
Wins 4 of 8 areas
Coding · Agents · Images and charts · Math
Qwen3.8 Max Preview wins more areas, narrowly.Gemini 3.1 Pro is better at reasoning.
Both rank among the ten best models we track in following instructions.
Scores updated · 43 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 own06Qwen3.8 Max Preview6 of 6 tests
- CodingWriting and fixing software24Qwen3.8 Max Preview4 of 6 tests
- MathCompetition and research-level math02Qwen3.8 Max Preview2 of 3 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video01Qwen3.8 Max Preview1 of 2 tests · 1 tie
- ReasoningHard problems that need careful thinking21Gemini 3.1 Pro2 of 4 tests · 1 tie
- FactsGetting facts right instead of making them up21Gemini 3.1 Pro2 of 3 tests
- Long documentsFinding answers in very long texts10Gemini 3.1 Pro1 of 1 test
- Following instructionsDoing exactly what it is asked11Even1 each
Long documents 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.
Qwen3.8 Max Preview costs 43% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Qwen3.8 Max Preview pulls ahead
- Real work tasks from 44 professionsGDPVal+43.7points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+34.9points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+26.4points ahead
Where Gemini 3.1 Pro pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+26.2points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+23.2points ahead
- Code for real scientific research problemsSciCode+6.6points ahead
Every test, side by side
All 43 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.8 Max Preview
- LMArena · WebDevQwen3.8 Max Preview by 225 rating points14471672+225 rating
- LiveBench · Agentic CodingQwen3.8 Max Preview by 20.644.164.7+20.6
- Terminal-Bench 2.1Qwen3.8 Max Preview by 1573.888.8+15
- SWE-bench ProQwen3.8 Max Preview by 13.554.267.7+13.5
- SciCodeGemini 3.1 Pro by 6.658.752.1+6.6
- LiveBench · CodingGemini 3.1 Pro by 3.676.572.9+3.6
AgentsQwen3.8 Max Preview
- GDPValQwen3.8 Max Preview by 43.714.658.3+43.7
- Terminal-Bench 4.0Qwen3.8 Max Preview by 34.9438.9+34.9
- τ-Bench V3 · BankingQwen3.8 Max Preview by 26.421.447.8+26.4
- AA ApexAgentsQwen3.8 Max Preview by 10.43242.4+10.4
- AA IT-Bench SREQwen3.8 Max Preview by 1030.340.3+10
- OSWorld-VerifiedQwen3.8 Max Preview by 9.976.286.1+9.9
ReasoningGemini 3.1 Pro
- LiveBench · ReasoningQwen3.8 Max Preview by 4.28488.2+4.2
- Humanity's Last ExamGemini 3.1 Pro by 3.94743.1+3.9
- GPQA DiamondGemini 3.1 Pro by 1.394.192.8+1.3
- CritPttie17.717.7tie
FactsGemini 3.1 Pro
- SimpleQA VerifiedGemini 3.1 Pro by 26.273.547.3+26.2
- AA-Omniscience · AccuracyGemini 3.1 Pro by 23.254.931.7+23.2
- AA-Omniscience · Non-hallucinationQwen3.8 Max Preview by 22.149.171.2+22.1
Images and chartsQwen3.8 Max Preview
- LMArena · VisionQwen3.8 Max Preview by 18 rating points12961314+18 rating
- MMMU-Protie82.482.8tie
MathQwen3.8 Max Preview
- FrontierMath Tier 4Qwen3.8 Max Preview by 19.526.846.3+19.5
- FrontierMath Tiers 1-3 (v2)Qwen3.8 Max Preview by 1559.674.7+15
- LiveBench · Mathematicstie9191.3tie
Following instructionsEven
- IFBenchQwen3.8 Max Preview by 5.777.182.8+5.7
- LiveBench · Instruction FollowingGemini 3.1 Pro by 579.174.1+5
Other results16 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.
- GDPval-AA v2Qwen3.8 Max Preview by 777 rating points9621739+777 rating
- DeepSWEQwen3.8 Max Preview by 46.61056.6+46.6
- DeepSWE 1.1Qwen3.8 Max Preview by 44.61256.6+44.6
- CyberGymQwen3.8 Max Preview by 39.738.878.5+39.7
- AA Agentic IndexQwen3.8 Max Preview by 39.310.349.6+39.3
- ToolathlonQwen3.8 Max Preview by 23.748.872.5+23.7
- NL2RepoQwen3.8 Max Preview by 22.533.455.9+22.5
- AA-OmniscienceGemini 3.1 Pro by 19.931.912+19.9
- AA IntelligenceQwen3.8 Max Preview by 15.729.745.4+15.7
- LVBenchQwen3.8 Max Preview by 15.666.281.8+15.6
- ERQAQwen3.8 Max Preview by 770.877.8+7
- livebench_languageGemini 3.1 Pro by 5.785.479.7+5.7
- HLE (with tools)Qwen3.8 Max Preview by 4.851.456.2+4.8
- Artificial Analysis Coding IndexQwen3.8 Max Preview by 368.871.8+3
- RealWorldQAQwen3.8 Max Preview by 2.685.488+2.6
- livebench_data_analysistie78.578.4tie
Questions people ask
Which is better, Gemini 3.1 Pro or Qwen3.8 Max Preview?
Qwen3.8 Max Preview wins four of the eight areas we test: coding, agents, images and charts and math. Gemini 3.1 Pro wins reasoning, facts and long documents. They are level on following instructions.
Which is better for coding?
Qwen3.8 Max Preview. It wins 4 of the 6 coding tests both models report; Gemini 3.1 Pro wins 2.
Which is cheaper?
Gemini 3.1 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; Qwen3.8 Max Preview costs $2.00 and $6.00. That makes Qwen3.8 Max Preview about 43% cheaper for the same work.
How do you compare the two?
We use the 43 benchmark tests both models have published scores on. The verdict counts the 27 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.