GPT-6.1 Sol vs Qwen3.8 2.4T A95B
GPT-6.1 Sol 
Qwen3.8 2.4T A95B Verdict
- GPT-6.1 Sol (max) leads on quality: 69.3 vs 63.3.
- GPT-6.1 Sol (max) is stronger in coding, composite, human preference, knowledge, long context, maths, multimodal, reasoning.
- Qwen3.8 2.4T A95B is stronger in agents & tools.
- Qwen3.8 2.4T A95B is 1.3× cheaper ($3.00 vs $4.00 per 1M blended).
- GPT-6.1 Sol (max) streams 1.5× faster (56 vs 37 tokens per second).
| Metric | GPT-6.1 Sol (max) | Qwen3.8 2.4T A95B |
|---|---|---|
| BenchLeader Index | 69.3 | 63.3 |
| Agents & tools score | 63.9 | 78.5 |
| Coding score | 72.4 | – |
| Composite score | 79.0 | 74.7 |
| Human preference score | 68.1 | – |
| Knowledge score | 78.8 | 63.6 |
| Long context score | 66.8 | 65.4 |
| Maths score | 72.5 | – |
| Multimodal score | 66.2 | – |
| Reasoning score | 76.4 | 74.5 |
| Blended price $/M | $4.00 | $3.00 |
| Output speed | 56 tok/s | 37 tok/s |
| Time to first answer | 326.9 s | 57.8 s |
| Context window | 1.1M | 1M |
| GPQA Diamond | 95.4% | – |
| FrontierMath Tiers 1–3 | 93.7% | – |
| FrontierMath Tier 4 | 100.0% | – |
| OTIS Mock AIME | 100.0% | – |
| SimpleQA Verified | 73.9% | – |
| Terminal-Bench | 58.2% | – |
| SciCode | 54.2% | – |
| APEX-Agents | 60.0% | – |
| LMArena Text | 1484 | – |
| LMArena Hard Prompts | 1507 | – |
| LMArena Coding | 1545 | – |
| LMArena WebDev | 1755 | – |
| LMArena Vision | 1288 | – |
| LMArena Agent | 11.7 | – |
| LiveBench | 81.6% | – |
| LiveBench Reasoning | 92.6% | – |
| LiveBench Coding | 80.4% | – |
| LiveBench Agentic Coding | 54.5% | – |
| LiveBench Mathematics | 96.8% | – |
| LiveBench Data Analysis | 82.7% | – |
| LiveBench Language | 90.1% | – |
| LiveBench Instruction Following | 74.2% | – |
| AA Intelligence Index v4.3.2 | 51.8 | 39.9 |
| AA-LCR | 83.0% | 80.3% |
| MMMU-Pro | 86.0% | – |
| AA-Omniscience | 41.5 | 4.3 |
| GPQA Diamond (AA) | – | 93.5% |
| Humanity's Last Exam (AA) | 52.9% | 42.5% |
| SciCode (AA) | 54.2% | 54.0% |
| IOI | 96.9% | – |
| Vals Index | 61.1 | – |
| ARC-AGI-1 | 96.5% | – |
| ARC-AGI-2 | 94.2% | – |
| ARC-AGI-3 | 96.2% | – |
| CritPt | 31.7% | 20.0% |
| GDPval-AA v2.1 | 53.8% | 55.6% |
| τ³-Banking (AA) | – | 49.1% |
| Analyst Agent (AA) | 50.0% | – |
| BioMysteryBench | 79.6% | – |
| Code Migration | 65.1% | – |
| CyberBench | 39.3% | – |
| Excel Modeling Benchmark | 70.8% | – |
| Finance Agent v2 | 52.0% | – |
| Harvey's Legal Agent Benchmark | 5.4% | – |
| Legal Research Bench | 38.5% | – |
| MedCode | 48.8% | – |
| MedScribe | 86.5% | – |
| MysteryMechanism | 46.4% | – |
| Public Benefits Bench | 59.3% | – |
| SAGE | 46.5% | – |
| SREBench | 50.8% | – |
| Tax Agent Bench | 62.3% | – |
| Terminal-Bench 4.0 (Vals) | 55.0% | – |
| Vibe Code Bench v1.1 | 88.9% | – |
| LMArena Maths | 1488 | – |
| LMArena Creative Writing | 1462 | – |
| LMArena Instruction Following | 1488 | – |
| LMArena Multi-turn | 1487 | – |
| LMArena Longer Queries | 1496 | – |
| Chess Puzzles | 61.0% | – |
| EBR-bench | 54.3% | – |
| Mystery Game Puzzles | 80.0% | – |
| Terminal-Bench 4.0 (AA) | 56.1% | 11.1% |
| Terminal-Bench 2.1 (AA) | – | 82.0% |
| AutomationBench | 64.9% | – |
| GDP.pdf | 31.0% | – |
| MLCR | 33.9% | – |
| Harvey LAB | 6.9% | – |
| AA-Omniscience: accuracy | 62.1% | 31.3% |
| AA-Omniscience: non-hallucination | 45.7% | 60.8% |
| AA-Briefcase v1.1 | 1557 | – |
Data as of 2026-10-11. Best configuration of each model; every score links to its source on the model pages.
GPT-6.1 Sol vs Qwen3.8 2.4T A95B: questions
- Is GPT-6.1 Sol better than Qwen3.8 2.4T A95B?
- GPT-6.1 Sol (max) leads on quality: 69.3 vs 63.3. The BenchLeader Index combines every independent quality benchmark; GPT-6.1 Sol (max) is ahead overall as of 2026-10-11, but check the category scores for your use.
- Is GPT-6.1 Sol better than Qwen3.8 2.4T A95B for agentic tasks?
- Qwen3.8 2.4T A95B scores higher in agentic tasks (79 vs 64 on the category index, where 50 is average).
- Which is cheaper, GPT-6.1 Sol or Qwen3.8 2.4T A95B?
- Qwen3.8 2.4T A95B is cheaper: $3.00 against $4.00 per million tokens, blended at three input tokens per output token.
- Which is faster, GPT-6.1 Sol or Qwen3.8 2.4T A95B?
- GPT-6.1 Sol streams faster: 56 against 37 output tokens per second.
- Which has the larger context window?
- GPT-6.1 Sol accepts more context: 1.1M against 1M tokens.