Qwen3 8 vs Qwen3.8 2.4T A95B
Qwen3 8 Verdict
- Qwen3 8 (max) leads on quality: 66.5 vs 65.2.
- Qwen3 8 (max) is stronger in coding, human preference, maths, multimodal.
- Qwen3.8 2.4T A95B is stronger in agents & tools, composite, knowledge, reasoning.
- They cost about the same ($2.67 per 1M blended).
| Metric | Qwen3 8 (max) | Qwen3.8 2.4T A95B |
|---|---|---|
| BenchLeader Index | 66.5 | 65.2 |
| Agents & tools score | 68.3 | 78.3 |
| Coding score | 66.5 | – |
| Composite score | 74.3 | 79.8 |
| Human preference score | 68.2 | – |
| Knowledge score | 63.5 | 66.3 |
| Long context score | 66.6 | 66.6 |
| Maths score | 67.0 | – |
| Multimodal score | 67.4 | – |
| Reasoning score | 76.3 | 80.5 |
| Blended price $/M | $2.67 | $3.00 |
| Output speed | 39 tok/s | 38 tok/s |
| Time to first answer | 55.1 s | 55.2 s |
| Context window | 1M | 984k |
| SciCode | 52.9% | – |
| ProofBench | 58.0% | – |
| Epoch Capabilities Index | 156.6 | – |
| LMArena Text | 1481 | – |
| LMArena Hard Prompts | 1503 | – |
| LMArena Coding | 1522 | – |
| LMArena WebDev | 1671 | – |
| LMArena Vision | 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 | 40.0 |
| AA-LCR | 80.3% | 80.3% |
| MMMU-Pro | 82.8% | – |
| AA-Omniscience | 12.0 | 4.3 |
| GPQA Diamond (AA) | 92.8% | 93.5% |
| Humanity's Last Exam (AA) | 43.1% | 42.5% |
| SciCode (AA) | 53.2% | 54.0% |
| 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% | 20.0% |
| GDPval (AA) | 58.2% | 56.4% |
| τ²-Bench Banking (AA) | 51.3% | 49.1% |
| 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 | 1498 | – |
| LMArena Creative Writing | 1472 | – |
| LMArena Instruction Following | 1477 | – |
| LMArena Multi-turn | 1495 | – |
| LMArena Longer Queries | 1492 | – |
Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.
Qwen3 8 vs Qwen3.8 2.4T A95B: questions
- Is Qwen3 8 better than Qwen3.8 2.4T A95B?
- Qwen3 8 (max) leads on quality: 66.5 vs 65.2. The BenchLeader Index combines every independent quality benchmark; Qwen3 8 (max) is ahead overall as of 2026-09-19, but check the category scores for your use.
- Is Qwen3 8 better than Qwen3.8 2.4T A95B for agentic tasks?
- Qwen3.8 2.4T A95B scores higher in agentic tasks (78 vs 68 on the category index, where 50 is average).
- Which is cheaper, Qwen3 8 or Qwen3.8 2.4T A95B?
- Qwen3 8 is cheaper: $2.67 against $3.00 per million tokens, blended at three input tokens per output token.
- Which is faster, Qwen3 8 or Qwen3.8 2.4T A95B?
- Qwen3 8 streams faster: 39 against 38 output tokens per second.
- Which has the larger context window?
- Qwen3 8 accepts more context: 1M against 984k tokens.