Model comparison
Seed 2.0 Pro vs Qwen2-72B
Seed 2.0 Pro is the stronger model overall, scoring 42.5 to 29.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
ByteDance Seed
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Seed 2.0 Pro scores higher in 8 categories and Qwen2-72B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Seed 2.0 Pro leads 63.0 to 41.0.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| Seed 2.0 Pro | Qwen2-72B | |
|---|---|---|
| Provider | ByteDance Seed | Alibaba (Qwen) |
| Noometry Index | 42.5 | 29.5 |
| Released | 2026-02-14 | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | 256K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $3 | — |
| Results tracked | 20 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Seed 2.0 Pro leads
Seed 2.0 Pro: 42.9 (#84), Qwen2-72B: 28.7 (#303)
| Benchmark | Seed 2.0 Pro | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1472 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Seed 2.0 Pro: —, Qwen2-72B: 16.9 (#138)
| Benchmark | Seed 2.0 Pro | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Too close to call
Seed 2.0 Pro: 23.1 (#167), Qwen2-72B: 22.2 (#184)
| Benchmark | Seed 2.0 Pro | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1453 | 1191 |
| NYT Connections (extended) | 28.4% | — |
| Thematic Generalization | 57.1% | — |
| Epoch Capabilities Index | — | 125.27 |
Math Seed 2.0 Pro leads
Seed 2.0 Pro: 36.5 (#110), Qwen2-72B: 27.9 (#232)
| Benchmark | Seed 2.0 Pro | Qwen2-72B |
|---|---|---|
| LMArena Math | 1440 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Seed 2.0 Pro leads
Seed 2.0 Pro: 39.6 (#119), Qwen2-72B: 21.2 (#270)
| Benchmark | Seed 2.0 Pro | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1440 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |
Multimodal Not comparable
Seed 2.0 Pro: 40.8 (#34), Qwen2-72B: —
| Benchmark | Seed 2.0 Pro | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1275 | — |
Multilingual Seed 2.0 Pro leads
Seed 2.0 Pro: 54.8 (#37), Qwen2-72B: 36.0 (#239)
| Benchmark | Seed 2.0 Pro | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1442 | 1176 |
| LMArena Chinese | 1490 | 1240 |
| LMArena French | 1470 | 1169 |
| LMArena German | 1443 | 1151 |
| LMArena Japanese | 1408 | 1111 |
| LMArena Korean | 1412 | 1083 |
| LMArena Russian | 1450 | 1169 |
| LMArena Spanish | 1460 | 1168 |
Instruction Following Seed 2.0 Pro leads
Seed 2.0 Pro: 74.7 (#86), Qwen2-72B: 62.0 (#236)
| Benchmark | Seed 2.0 Pro | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1414 | 1181 |
Long Context Seed 2.0 Pro leads
Seed 2.0 Pro: 43.6 (#85), Qwen2-72B: 36.1 (#230)
| Benchmark | Seed 2.0 Pro | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1428 | 1193 |
Writing & Preference Seed 2.0 Pro leads
Seed 2.0 Pro: 63.0 (#66), Qwen2-72B: 41.0 (#236)
| Benchmark | Seed 2.0 Pro | Qwen2-72B |
|---|---|---|
| LMArena Text | 1448 | 1203 |
| LMArena Creative Writing | 1406 | 1181 |
| LMArena Multi-Turn | 1441 | 1195 |
Frequently asked questions
Is Seed 2.0 Pro better than Qwen2-72B?
Seed 2.0 Pro is the stronger model overall, scoring 42.5 to 29.5 on the Noometry Index.
Is Seed 2.0 Pro or Qwen2-72B better for coding?
Seed 2.0 Pro scores higher on coding benchmarks: 42.9 versus 28.7 in the Noometry coding category.
How many benchmarks do Seed 2.0 Pro and Qwen2-72B share?
17 benchmarks have published results for both models. Seed 2.0 Pro has 20 scored results on Noometry and Qwen2-72B has 26.