Seed2.1 wins more areas, narrowly.Claude Opus 4.7 is better at reasoning.
Both rank among the ten best models we track in images and charts.
Scores updated · 31 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.
Reasoning 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.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Seed2.1 pulls ahead
Where Claude Opus 4.7 pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+15.5points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+14.5points ahead
- Long professional tasks in banking, consulting and lawAA ApexAgents+4.7points ahead
Every test, side by side
All 31 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- Terminal-Bench 2.1Claude Opus 4.7 by 15.583.167.6+15.5
- SciCodeSeed2.1 by 3.354.557.8+3.3
AgentsSeed2.1
- GDPValSeed2.1 by 40.142.682.7+40.1
- AA ApexAgentsClaude Opus 4.7 by 4.733.929.2+4.7
- MCP AtlasSeed2.1 by 377.380.3+3
Images and chartsSeed2.1
- BLINKSeed2.1 by 970.479.4+9
- MathVistaSeed2.1 by 6.184.490.5+6.1
- OCRBenchv2Seed2.1 by 5.956.962.8+5.9
- MMMU-ProSeed2.1 by 1.378.880.1+1.3
Other results21 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.
- BabyVisionSeed2.1 by 40.722.262.9+40.7
- DeepSWEClaude Opus 4.7 by 315423+31
- VisuLogicSeed2.1 by 20.332.652.9+20.3
- ERQASeed2.1 by 18.852.571.3+18.8
- OfficeQA ProClaude Opus 4.7 by 17.880.662.8+17.8
- SimpleVQASeed2.1 by 14.656.571.1+14.6
- MMSIBench (circular)Seed2.1 by 1417.431.4+14
- WorldVQASeed2.1 by 12.735.948.6+12.7
- ZeroBench (sub)Seed2.1 by 1237.149.1+12
- MathVerse (Vision-Only)Seed2.1 by 11.877.489.2+11.8
- RealWorldQASeed2.1 by 10.775.686.3+10.7
- ToolathlonClaude Opus 4.7 by 10.259.349.1+10.2
- Finance Agent v1.1Claude Opus 4.7 by 8.464.456+8.4
- SWE-Pro BenchClaude Opus 4.7 by 7.364.357+7.3
- CyberGymClaude Opus 4.7 by 6.173.167+6.1
- ChartQAProSeed2.1 by 5.465.570.9+5.4
- Office QA Pro [Multimodal]Claude Opus 4.7 by 5.476.571.1+5.4
- EmbSpatial-BenchSeed2.1 by 5.377.282.5+5.3
- DynaMathSeed2.1 by 563.168.1+5
- ZeroBench (main)Seed2.1 by 3811+3
- DUDEClaude Opus 4.7 by 1.484.583.1+1.4
Questions people ask
Which is better, Claude Opus 4.7 or Seed2.1?
Seed2.1 wins two of the four areas where both have results: agents and images and charts. Claude Opus 4.7 wins reasoning. They are level on coding.
Which is better for coding?
Neither. They win 1 coding test each of the 2 both models report.
How do you compare the two?
We use the 31 benchmark tests both models have published scores on. The verdict counts the 10 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 21 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.