Gemini 3.1 Pro vs Seed 1.8
Wins 4 of 4 areas
Coding · Agents · Images and charts · Following instructions
Wins 0 of 4 areas
—
Gemini 3.1 Pro is the stronger all-rounder.Seed 1.8 is cheaper.
Scores updated · 24 tests both models report · How we compare
Where each one wins
Tests won in each of the four 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.
Following instructions 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.
Seed 1.8 costs 84% 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 Gemini 3.1 Pro pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+18.3points ahead
- Completes tasks by operating a computer desktopOSWorld-Verified+14.3points ahead
- Recent programming contest problemsLiveCodeBench v6+12.2points ahead
Where Seed 1.8 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 24 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGemini 3.1 Pro
- LiveCodeBench v6Gemini 3.1 Pro by 12.291.779.5+12.2
- SWE-bench VerifiedGemini 3.1 Pro by 7.780.672.9+7.7
AgentsGemini 3.1 Pro
- BrowseCompGemini 3.1 Pro by 18.385.967.6+18.3
- OSWorld-VerifiedGemini 3.1 Pro by 14.376.261.9+14.3
Images and chartsGemini 3.1 Pro
- CharXiv (RQ)Gemini 3.1 Pro by 11.983.371.4+11.9
- MMMU-ProGemini 3.1 Pro by 9.282.473.2+9.2
- BLINKGemini 3.1 Pro by 4.879.174.3+4.8
- MathVistaGemini 3.1 Pro by 2.590.287.7+2.5
Following instructionsGemini 3.1 Pro
- Multi-ChallengeGemini 3.1 Pro by 4.771.466.7+4.7
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.
- Terminal-Bench 2.0Gemini 3.1 Pro by 23.368.545.2+23.3
- DUDEGemini 3.1 Pro by 12.782.169.4+12.7
- ERQAGemini 3.1 Pro by 1270.858.8+12
- DynaMathGemini 3.1 Pro by 10.672.161.5+10.6
- MATH-VisionGemini 3.1 Pro by 8.589.881.3+8.5
- LVBenchSeed 1.8 by 6.866.273+6.8
- OVBenchSeed 1.8 by 6.358.865.1+6.3
- MMLU-ProGemini 3.1 Pro by 6.19184.9+6.1
- SimpleVQAGemini 3.1 Pro by 4.569.965.4+4.5
- VideoSimpleQAGemini 3.1 Pro by 2.27067.8+2.2
- MinervaGemini 3.1 Pro by 1.163.562.4+1.1
- LongVideoBenchtie76.577.4tie
- MotionBenchtie69.970.6tie
- TVBenchtie7171.5tie
- TOMATOtie60.460.8tie
Questions people ask
Which is better, Gemini 3.1 Pro or Seed 1.8?
Gemini 3.1 Pro wins all four areas where both have results: coding, agents, images and charts and following instructions. Seed 1.8 wins none, but costs 84% less.
Which is better for coding?
Gemini 3.1 Pro. It wins 2 of the 2 coding tests both models report; Seed 1.8 wins none.
Which is cheaper?
Gemini 3.1 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; Seed 1.8 costs $0.25 and $2.00. That makes Seed 1.8 about 84% cheaper for the same work.
How do you compare the two?
We use the 24 benchmark tests both models have published scores on. The verdict counts the 9 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.