Dola Seed 2.0 Pro vs Qwen3 8
Dola Seed 2.0 Pro 
Qwen3 8 Verdict
- Qwen3 8 (max) leads on quality: 66.6 vs 59.2.
- Qwen3 8 (max) is stronger in coding, human preference, maths, multimodal, reasoning, agents & tools, composite, knowledge, long context.
| Metric | Dola Seed 2.0 Pro | Qwen3 8 (max) |
|---|---|---|
| BenchLeader Index | 59.2 | 66.6 |
| Coding score | 66.1 | 66.5 |
| Human preference score | 65.2 | 68.3 |
| Maths score | 64.2 | 67.1 |
| Multimodal score | 62.3 | 67.4 |
| Reasoning score | 65.5 | 76.3 |
| Agents & tools score | – | 68.3 |
| Composite score | – | 74.4 |
| Knowledge score | – | 63.5 |
| Long context score | – | 66.6 |
| Blended price $/M | – | $2.67 |
| Output speed | – | 39 tok/s |
| Time to first answer | – | 56.5 s |
| Context window | – | 1M |
| SciCode | – | 52.9% |
| ProofBench | – | 58.0% |
| Epoch Capabilities Index | – | 156.6 |
| LMArena Text | 1456 | 1481 |
| LMArena Hard Prompts | 1480 | 1503 |
| LMArena Coding | 1513 | 1522 |
| LMArena WebDev | – | 1671 |
| LMArena Vision | 1275 | 1315 |
| LMArena Agent | – | 3.3 |
| LiveBench | – | 78.5% |
| LiveBench Reasoning | – | 88.2% |
| LiveBench Coding | – | 72.9% |
| LiveBench Agentic Coding | – | 64.7% |
| LiveBench Mathematics | – | 91.3% |
| LiveBench Data Analysis | – | 78.4% |
| LiveBench Language | – | 79.7% |
| LiveBench Instruction Following | – | 74.1% |
| AA Intelligence Index | – | 45.4 |
| AA-LCR | – | 80.3% |
| MMMU-Pro | – | 82.8% |
| AA-Omniscience | – | 12.0 |
| GPQA Diamond (AA) | – | 92.8% |
| Humanity's Last Exam (AA) | – | 43.1% |
| SciCode (AA) | – | 53.2% |
| LiveCodeBench | – | 87.8% |
| MMLU-Pro | – | 88.6% |
| IOI | – | 68.9% |
| LegalBench | – | 83.6% |
| CorpFin | – | 65.8% |
| TaxEval | – | 75.5% |
| Terminal-Bench 2.1 (Vals) | – | 67.4% |
| SWE-bench (Vals) | – | 85.6% |
| GPQA Diamond (Vals) | – | 93.7% |
| Vals Index | – | 51.8 |
| CritPt | – | 20.0% |
| GDPval (AA) | – | 58.4% |
| τ²-Bench Banking (AA) | – | 51.3% |
| Code Migration | – | 24.0% |
| Excel Modeling Benchmark | – | 60.1% |
| Finance Agent v2 | – | 50.6% |
| Harvey's Legal Agent Benchmark | – | 10.4% |
| Legal Research Bench | – | 47.6% |
| MedCode | – | 40.7% |
| MedScribe | – | 85.0% |
| MMMU-Pro (Vals) | – | 88.0% |
| MortgageTax | – | 64.0% |
| MysteryMechanism | – | 23.9% |
| ProgramBench | – | 0.0% |
| Public Benefits Bench | – | 67.1% |
| SAGE | – | 51.3% |
| SkillsBench | – | 42.0% |
| Tax Agent Bench | – | 66.0% |
| Terminal-Bench 4.0 (Vals) | – | 24.8% |
| Terminal-Bench Science | – | 1.4% |
| Vals Multimodal Index | – | 65.4% |
| Vibe Code Bench 1-100 | – | 12.8% |
| Vibe Code Bench v1.1 | – | 64.7% |
| LMArena Maths | 1451 | 1498 |
| LMArena Creative Writing | 1402 | 1472 |
| LMArena Instruction Following | 1434 | 1477 |
| LMArena Multi-turn | 1448 | 1495 |
| LMArena Longer Queries | 1451 | 1492 |
Data as of 2026-09-20. Best configuration of each model; every score links to its source on the model pages.
Dola Seed 2.0 Pro vs Qwen3 8: questions
- Is Dola Seed 2.0 Pro better than Qwen3 8?
- Qwen3 8 (max) leads on quality: 66.6 vs 59.2. The BenchLeader Index combines every independent quality benchmark; Qwen3 8 (max) is ahead overall as of 2026-09-20, but check the category scores for your use.
- Is Dola Seed 2.0 Pro better than Qwen3 8 for coding?
- Qwen3 8 scores higher in coding (67 vs 66 on the category index, where 50 is average).