Gemini 3.1 Pro wins more areas, narrowly.Seed 2.1 Turbo is cheaper and better at images and charts.
Both rank among the ten best models we track in images and charts.
Scores updated · 44 tests both models report · How we compare
Where each one wins
Tests won in each of the five 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.
- AgentsCarrying out multi-step tasks on its own21Gemini 3.1 Pro2 of 4 tests · 1 tie
- FactsGetting facts right instead of making them up10Gemini 3.1 Pro1 of 1 test
- Images and chartsUnderstanding pictures, charts and video01Seed 2.1 Turbo1 of 6 tests · 5 ties
- CodingWriting and fixing software11Even1 each · 1 tie
- ReasoningHard problems that need careful thinking11Even1 each
Facts 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 2.1 Turbo costs 79% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Gemini 3.1 Pro pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+43.8points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+15.8points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+6.2points ahead
Where Seed 2.1 Turbo pulls ahead
- Multi-step tasks using many real software toolsMCP Atlas+11.1points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+7.6points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+2.8points ahead
Every test, side by side
All 44 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- Terminal-Bench 2.1Gemini 3.1 Pro by 6.273.867.6+6.2
- SWE-bench ProSeed 2.1 Turbo by 2.854.257+2.8
- SciCodetie58.757.8tie
AgentsGemini 3.1 Pro
- MCP AtlasSeed 2.1 Turbo by 11.169.280.3+11.1
- AA ApexAgentsGemini 3.1 Pro by 2.83229.2+2.8
- BrowseCompGemini 3.1 Pro by 185.984.9+1
- OSWorld-Verifiedtie76.276.4tie
ReasoningEven
- ARC-AGI-2Gemini 3.1 Pro by 15.877.161.3+15.8
- Humanity's Last ExamSeed 2.1 Turbo by 7.64754.6+7.6
Images and chartsSeed 2.1 Turbo
- Video-MMESeed 2.1 Turbo by 2.386.789+2.3
- BLINKtie79.179.4tie
- CharXiv (RQ)tie83.383.6tie
- MathVistatie90.290.5tie
- MMMU-Protie82.482.2tie
- OCRBenchv2tie62.862.8tie
Other results28 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.
- CyberGymSeed 2.1 Turbo by 28.238.867+28.2
- DeepSWESeed 2.1 Turbo by 131023+13
- OVBenchSeed 2.1 Turbo by 10.958.869.7+10.9
- LVBenchSeed 2.1 Turbo by 10.666.276.8+10.6
- NL2RepoSeed 2.1 Turbo by 10.333.443.7+10.3
- Program BenchSeed 2.1 Turbo by 9.939.549.4+9.9
- BabyVisionSeed 2.1 Turbo by 8.554.462.9+8.5
- MMLongBench-128KSeed 2.1 Turbo by 6.270.776.9+6.2
- TVBenchSeed 2.1 Turbo by 6.27177.2+6.2
- MotionBenchSeed 2.1 Turbo by 4.969.974.8+4.9
- WorldVQASeed 2.1 Turbo by 4.344.348.6+4.3
- LongVideoBenchSeed 2.1 Turbo by 4.176.580.6+4.1
- DynaMathGemini 3.1 Pro by 472.168.1+4
- Finance Agent v1.1Gemini 3.1 Pro by 3.759.756+3.7
- TOMATOGemini 3.1 Pro by 3.660.456.8+3.6
- PostTrainBenchGemini 3.1 Pro by 3.321.618.3+3.3
- MATH-VisionSeed 2.1 Turbo by 2.989.892.7+2.9
- MinervaSeed 2.1 Turbo by 2.463.565.9+2.4
- EmbSpatial-BenchGemini 3.1 Pro by 1.784.282.5+1.7
- VideoHolmesSeed 2.1 Turbo by 1.765.967.6+1.7
- OfficeQA ProGemini 3.1 Pro by 1.472.571.1+1.4
- VideoSimpleQASeed 2.1 Turbo by 1.47071.4+1.4
- SimpleVQASeed 2.1 Turbo by 1.269.971.1+1.2
- DUDESeed 2.1 Turbo by 182.183.1+1
- RealWorldQAtie85.486.3tie
- ChartQAProtie70.270.9tie
- ERQAtie70.871.3tie
- Toolathlontie48.849.1tie
Questions people ask
Which is better, Gemini 3.1 Pro or Seed 2.1 Turbo?
Gemini 3.1 Pro wins two of the five areas where both have results: agents and facts. Seed 2.1 Turbo wins images and charts, and costs 79% less. They are level on coding and reasoning.
Which is better for coding?
Neither. They win 1 coding test each of the 3 both models report, and 1 is a tie.
Which is cheaper?
Gemini 3.1 Pro costs $2.00 per million input tokens and $12.00 per million output tokens; Seed 2.1 Turbo costs $0.50 and $2.50. That makes Seed 2.1 Turbo about 79% cheaper for the same work.
How do you compare the two?
We use the 44 benchmark tests both models have published scores on. The verdict counts the 16 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 28 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.