Model comparison
Seed 2.0 Pro vs gpt-oss-120b
Seed 2.0 Pro is the stronger model overall, scoring 43.2 to 36.3 on the Noometry Index. gpt-oss-120b costs 16× less per token, which makes it the better buy when Seed 2.0 Pro's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
ByteDance SeedSummary
- They share 17 benchmarks with published results for both. Seed 2.0 Pro scores higher in 6 categories and gpt-oss-120b in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Seed 2.0 Pro leads 62.9 to 46.5.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.50 / $3 for Seed 2.0 Pro.
- Seed 2.0 Pro accepts more context: 256K tokens versus 131K.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| Seed 2.0 Pro | gpt-oss-120b | |
|---|---|---|
| Provider | ByteDance Seed | OpenAI |
| Noometry Index | 43.2 | 36.3 |
| Released | 2026-02-14 | 2025-08-05 |
| Weights | Proprietary | Open |
| Context window | 256K | 131K |
| Max output | 128K | 41K |
| Input $ / M tokens | $0.50 | $0.037 |
| Output $ / M tokens | $3 | $0.17 |
| Results tracked | 20 | 48 |
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: 43.5 (#86), gpt-oss-120b: 33.5 (#256)
| Benchmark | Seed 2.0 Pro | gpt-oss-120b |
|---|---|---|
| LMArena Coding | 1472 | 1380 |
| SWE-bench Verified (bash only) | — | 26% |
| Aider Polyglot | — | 41.8% |
| SciCode | — | 36% |
| WeirdML | — | 48.2% |
| ALE-Bench | — | 575.62 |
| AlgoTune | — | 1.41 |
Agentic & Tool Use Not comparable
Seed 2.0 Pro: —, gpt-oss-120b: 12.2 (#153)
| Benchmark | Seed 2.0 Pro | gpt-oss-120b |
|---|---|---|
| Terminal-Bench | — | 18.7% |
| APEX-Agents | — | 4.4% |
| METR Time Horizons | — | 56.6% |
| Vending-Bench 2 | — | -21.53 |
Reasoning Seed 2.0 Pro leads
Seed 2.0 Pro: 24.1 (#165), gpt-oss-120b: 20.0 (#245)
| Benchmark | Seed 2.0 Pro | gpt-oss-120b |
|---|---|---|
| LMArena Hard Prompts | 1453 | 1364 |
| SimpleBench | — | 22.1% |
| Kagi LLM Benchmark | — | 58.6% |
| NYT Connections (extended) | 28.4% | — |
| CritPt | — | 1.1% |
| Chess Puzzles | — | 20% |
| Thematic Generalization | 57.1% | — |
| Mystery Game Puzzles | — | 2% |
| DTBench | — | 76.3% |
| LMCA | — | 22.1% |
| Surface Evolver Bench | — | 25% |
| Epoch Capabilities Index | — | 139.93 |
Math gpt-oss-120b leads
Seed 2.0 Pro: 39.3 (#108), gpt-oss-120b: 52.5 (#50)
| Benchmark | Seed 2.0 Pro | gpt-oss-120b |
|---|---|---|
| LMArena Math | 1439 | 1389 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| Omni-MATH | — | 68.8% |
Knowledge gpt-oss-120b leads
Seed 2.0 Pro: 40.2 (#122), gpt-oss-120b: 42.4 (#96)
| Benchmark | Seed 2.0 Pro | gpt-oss-120b |
|---|---|---|
| LMArena Expert | 1440 | 1356 |
| GPQA Diamond | — | 75.8% |
| MMLU-Pro | — | 79.5% |
| Confabulations | — | 15.7% |
| Vectara Hallucination Rate | — | 14.2% |
| GPQA (HELM) | — | 68.4% |
Multimodal Not comparable
Seed 2.0 Pro: 41.5 (#35), gpt-oss-120b: —
| Benchmark | Seed 2.0 Pro | gpt-oss-120b |
|---|---|---|
| LMArena Vision | 1274 | — |
Multilingual Seed 2.0 Pro leads
Seed 2.0 Pro: 54.5 (#39), gpt-oss-120b: 48.0 (#147)
| Benchmark | Seed 2.0 Pro | gpt-oss-120b |
|---|---|---|
| LMArena Non-English | 1441 | 1351 |
| LMArena Chinese | 1489 | 1385 |
| LMArena French | 1471 | 1369 |
| LMArena German | 1442 | 1353 |
| LMArena Japanese | 1408 | 1331 |
| LMArena Korean | 1411 | 1282 |
| LMArena Russian | 1449 | 1343 |
| LMArena Spanish | 1460 | 1389 |
Instruction Following Seed 2.0 Pro leads
Seed 2.0 Pro: 74.5 (#91), gpt-oss-120b: 69.3 (#173)
| Benchmark | Seed 2.0 Pro | gpt-oss-120b |
|---|---|---|
| LMArena Instruction Following | 1414 | 1318 |
| IFEval | — | 83.6% |
Long Context Seed 2.0 Pro leads
Seed 2.0 Pro: 43.6 (#90), gpt-oss-120b: 31.4 (#278)
| Benchmark | Seed 2.0 Pro | gpt-oss-120b |
|---|---|---|
| LMArena Longer Query | 1428 | 1319 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference Seed 2.0 Pro leads
Seed 2.0 Pro: 62.9 (#69), gpt-oss-120b: 46.5 (#217)
| Benchmark | Seed 2.0 Pro | gpt-oss-120b |
|---|---|---|
| LMArena Text | 1448 | 1365 |
| LMArena Creative Writing | 1406 | 1275 |
| LMArena Multi-Turn | 1441 | 1340 |
| Short-Story Creative Writing | — | 77.1% |
| EQ-Bench Creative Writing | — | 961 |
| WildBench | — | 84.5% |
Frequently asked questions
Is Seed 2.0 Pro better than gpt-oss-120b?
Seed 2.0 Pro is the stronger model overall, scoring 43.2 to 36.3 on the Noometry Index. gpt-oss-120b costs 16× less per token, which makes it the better buy when Seed 2.0 Pro's lead doesn't matter for your workload.
Which is cheaper, Seed 2.0 Pro or gpt-oss-120b?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Seed 2.0 Pro lists at $0.50 and $3.
Is Seed 2.0 Pro or gpt-oss-120b better for coding?
Seed 2.0 Pro scores higher on coding benchmarks: 43.5 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Seed 2.0 Pro does, with 256K tokens against 131K.
How many benchmarks do Seed 2.0 Pro and gpt-oss-120b share?
17 benchmarks have published results for both models. Seed 2.0 Pro has 20 scored results on Noometry and gpt-oss-120b has 48.