Model comparison
Claude 3.7 Sonnet vs Seed 2.0 Pro
Seed 2.0 Pro is the stronger model overall, scoring 43.2 to 39.5 on the Noometry Index.
Last verified . 18 shared benchmarks.
ByteDance SeedSummary
- They share 18 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 1 category and Seed 2.0 Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Seed 2.0 Pro leads 54.5 to 44.1.
Side by side
| Claude 3.7 Sonnet | Seed 2.0 Pro | |
|---|---|---|
| Provider | Anthropic | ByteDance Seed |
| Noometry Index | 39.5 | 43.2 |
| Released | 2025-02-24 | 2026-02-14 |
| Weights | Proprietary | Proprietary |
| Context window | — | 256K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $3 |
| Results tracked | 58 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Seed 2.0 Pro leads
Claude 3.7 Sonnet: 40.6 (#136), Seed 2.0 Pro: 43.5 (#86)
| Benchmark | Claude 3.7 Sonnet | Seed 2.0 Pro |
|---|---|---|
| LMArena Coding | 1361 | 1472 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| GSO | 3.8% | — |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
Agentic & Tool Use Not comparable
Claude 3.7 Sonnet: 34.1 (#50), Seed 2.0 Pro: —
| Benchmark | Claude 3.7 Sonnet | Seed 2.0 Pro |
|---|---|---|
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
Reasoning Seed 2.0 Pro leads
Claude 3.7 Sonnet: 18.6 (#277), Seed 2.0 Pro: 24.1 (#165)
| Benchmark | Claude 3.7 Sonnet | Seed 2.0 Pro |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1453 |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| NYT Connections (extended) | — | 28.4% |
| ARC-AGI-1 | 28.6% | — |
| EnigmaEval | 4.2% | — |
| Thematic Generalization | — | 57.1% |
| LiveBench Reasoning | 87.8% | — |
| LiveBench Data Analysis | 74% | — |
| Epoch Capabilities Index | 141.16 | — |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |
Math Seed 2.0 Pro leads
Claude 3.7 Sonnet: 37.5 (#153), Seed 2.0 Pro: 39.3 (#108)
| Benchmark | Claude 3.7 Sonnet | Seed 2.0 Pro |
|---|---|---|
| LMArena Math | 1337 | 1439 |
| OTIS Mock AIME 2024-2025 | 57.8% | — |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Too close to call
Claude 3.7 Sonnet: 39.8 (#130), Seed 2.0 Pro: 40.2 (#122)
| Benchmark | Claude 3.7 Sonnet | Seed 2.0 Pro |
|---|---|---|
| LMArena Expert | 1321 | 1440 |
| GPQA Diamond | 79.7% | — |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |
Multimodal Seed 2.0 Pro leads
Claude 3.7 Sonnet: 33.7 (#95), Seed 2.0 Pro: 41.5 (#35)
| Benchmark | Claude 3.7 Sonnet | Seed 2.0 Pro |
|---|---|---|
| LMArena Vision | 1169 | 1274 |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Seed 2.0 Pro leads
Claude 3.7 Sonnet: 44.1 (#179), Seed 2.0 Pro: 54.5 (#39)
| Benchmark | Claude 3.7 Sonnet | Seed 2.0 Pro |
|---|---|---|
| LMArena Non-English | 1296 | 1441 |
| LMArena Chinese | 1299 | 1489 |
| LMArena French | 1303 | 1471 |
| LMArena German | 1301 | 1442 |
| LMArena Japanese | 1267 | 1408 |
| LMArena Korean | 1249 | 1411 |
| LMArena Russian | 1311 | 1449 |
| LMArena Spanish | 1298 | 1460 |
Instruction Following Seed 2.0 Pro leads
Claude 3.7 Sonnet: 72.9 (#125), Seed 2.0 Pro: 74.5 (#91)
| Benchmark | Claude 3.7 Sonnet | Seed 2.0 Pro |
|---|---|---|
| LMArena Instruction Following | 1352 | 1414 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), Seed 2.0 Pro: 43.6 (#90)
| Benchmark | Claude 3.7 Sonnet | Seed 2.0 Pro |
|---|---|---|
| LMArena Longer Query | 1373 | 1428 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Seed 2.0 Pro leads
Claude 3.7 Sonnet: 54.4 (#150), Seed 2.0 Pro: 62.9 (#69)
| Benchmark | Claude 3.7 Sonnet | Seed 2.0 Pro |
|---|---|---|
| LMArena Text | 1314 | 1448 |
| LMArena Creative Writing | 1332 | 1406 |
| LMArena Multi-Turn | 1339 | 1441 |
| Short-Story Creative Writing | 81.1% | — |
| EQ-Bench Creative Writing | 1412 | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Seed 2.0 Pro?
Seed 2.0 Pro is the stronger model overall, scoring 43.2 to 39.5 on the Noometry Index.
Is Claude 3.7 Sonnet or Seed 2.0 Pro better for coding?
Seed 2.0 Pro scores higher on coding benchmarks: 43.5 versus 40.6 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Seed 2.0 Pro share?
18 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Seed 2.0 Pro has 20.