Model comparison
DeepSeek-V2.5 (Sep 2024) vs Seed 2.0 Pro
Seed 2.0 Pro is the stronger model overall, scoring 43.2 to 37.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
ByteDance SeedSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 1 category and Seed 2.0 Pro in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Seed 2.0 Pro leads 62.9 to 49.8.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Seed 2.0 Pro | |
|---|---|---|
| Provider | DeepSeek | ByteDance Seed |
| Noometry Index | 37.6 | 43.2 |
| Released | 2024-09-06 | 2026-02-14 |
| Weights | Open | Proprietary |
| Context window | — | 256K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $3 |
| Results tracked | 22 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Seed 2.0 Pro leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Seed 2.0 Pro: 43.5 (#86)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Seed 2.0 Pro |
|---|---|---|
| LMArena Coding | 1309 | 1472 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Seed 2.0 Pro: 24.1 (#165)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Seed 2.0 Pro |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1453 |
| NYT Connections (extended) | — | 28.4% |
| Thematic Generalization | — | 57.1% |
Math Seed 2.0 Pro leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Seed 2.0 Pro: 39.3 (#108)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Seed 2.0 Pro |
|---|---|---|
| LMArena Math | 1288 | 1439 |
Knowledge Seed 2.0 Pro leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Seed 2.0 Pro: 40.2 (#122)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Seed 2.0 Pro |
|---|---|---|
| LMArena Expert | 1266 | 1440 |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, Seed 2.0 Pro: 41.5 (#35)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Seed 2.0 Pro |
|---|---|---|
| LMArena Vision | — | 1274 |
Multilingual Seed 2.0 Pro leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Seed 2.0 Pro: 54.5 (#39)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Seed 2.0 Pro |
|---|---|---|
| LMArena Non-English | 1273 | 1441 |
| LMArena Chinese | 1318 | 1489 |
| LMArena French | 1289 | 1471 |
| LMArena German | 1258 | 1442 |
| LMArena Japanese | 1228 | 1408 |
| LMArena Korean | 1209 | 1411 |
| LMArena Russian | 1289 | 1449 |
| LMArena Spanish | 1248 | 1460 |
Instruction Following Seed 2.0 Pro leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Seed 2.0 Pro: 74.5 (#91)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Seed 2.0 Pro |
|---|---|---|
| LMArena Instruction Following | 1280 | 1414 |
Long Context Seed 2.0 Pro leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Seed 2.0 Pro: 43.6 (#90)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Seed 2.0 Pro |
|---|---|---|
| LMArena Longer Query | 1301 | 1428 |
Writing & Preference Seed 2.0 Pro leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Seed 2.0 Pro: 62.9 (#69)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Seed 2.0 Pro |
|---|---|---|
| LMArena Text | 1294 | 1448 |
| LMArena Creative Writing | 1285 | 1406 |
| LMArena Multi-Turn | 1297 | 1441 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Seed 2.0 Pro?
Seed 2.0 Pro is the stronger model overall, scoring 43.2 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Seed 2.0 Pro better for coding?
Seed 2.0 Pro scores higher on coding benchmarks: 43.5 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Seed 2.0 Pro share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Seed 2.0 Pro has 20.