GPT-5.2 vs GPT-6 Sol
GPT-5.2 Verdict
- GPT-6 Sol (max) leads on quality: 67.7 vs 61.4.
- GPT-5.2 (xhigh) is stronger in agents & tools, coding, instruction following, maths.
- GPT-6 Sol (max) is stronger in composite, knowledge, long context, reasoning, multimodal.
- GPT-6 Sol (max) is 1.2× cheaper ($4.00 vs $4.81 per 1M blended).
- GPT-6 Sol (max) streams 1.6× faster (126 vs 80 tokens per second).
| Metric | GPT-5.2 (xhigh) | GPT-6 Sol (max) |
|---|---|---|
| BenchLeader Index | 61.4 | 67.7 |
| Agents & tools score | 54.8 | – |
| Coding score | 63.0 | – |
| Composite score | 65.7 | 86.2 |
| Instruction following score | 73.4 | – |
| Knowledge score | 57.6 | 75.4 |
| Long context score | 67.2 | 67.7 |
| Maths score | 58.4 | – |
| Reasoning score | 62.1 | 95.0 |
| Multimodal score | – | 67.1 |
| Blended price $/M | $4.81 | $4.00 |
| Output speed | 80 tok/s | 126 tok/s |
| Time to first answer | 175.3 s | 107.2 s |
| Context window | 400k | 1.1M |
| GPQA Diamond | 91.4% | – |
| FrontierMath Tiers 1–3 | 67.4% | – |
| FrontierMath Tier 4 | 31.7% | – |
| OTIS Mock AIME | 96.1% | – |
| SimpleQA Verified | 37.1% | – |
| WeirdML | 72.2% | – |
| ProofBench | 15.0% | – |
| AA Intelligence Index | 30.4 | 47.5 |
| IFBench | 75.4% | – |
| AA-LCR | 82.7% | 83.7% |
| MMMU-Pro | – | 83.3% |
| AA-Omniscience | -0.9 | 27.1 |
| Terminal-Bench Hard | 47.0% | – |
| GPQA Diamond (AA) | 90.3% | – |
| Humanity's Last Exam (AA) | 37.7% | 47.9% |
| SciCode (AA) | – | 57.6% |
| τ²-Bench Telecom (AA) | 84.8% | – |
| AIME (Vals) | 96.9% | – |
| LiveCodeBench | 85.4% | – |
| MMLU-Pro | 86.2% | – |
| LegalBench | 82.8% | – |
| CorpFin | 65.9% | – |
| TaxEval | 75.8% | – |
| MedQA | 94.1% | – |
| MGSM | 94.0% | – |
| SWE-bench (Vals) | 75.8% | – |
| GPQA Diamond (Vals) | 91.7% | – |
| MCP Atlas | 67.6% | – |
| ARC-AGI-1 | 86.2% | – |
| ARC-AGI-2 | 52.9% | – |
| CritPt | 11.6% | 30.9% |
| GDPval (AA) | – | 49.4% |
| CaseLaw v2 | 66.0% | – |
| MedCode | 49.8% | – |
| MedScribe | 84.4% | – |
| MMMU-Pro (Vals) | 86.7% | – |
| MortgageTax | 67.1% | – |
| SAGE | 49.3% | – |
| Vibe Code Bench v1.1 | 53.5% | – |
| DrugDiscoveryBench | 29.3% | – |
| Chess Puzzles | 49.0% | – |
| EBR-bench | 23.0% | – |
| VPCT | 84.0% | – |
| LMCA | 43.9% | – |
| DTBench | 90.9% | – |
| Terminal-Bench 4.0 (AA) | – | 43.9% |
| AutomationBench | – | 61.6% |
| GDP.pdf | – | 24.8% |
| MLCR | – | 16.1% |
| AA-Omniscience: accuracy | 44.3% | 54.5% |
| AA-Omniscience: non-hallucination | 18.8% | 39.9% |
| AA-Briefcase | – | 1483 |
Data as of 2026-09-23. Best configuration of each model; every score links to its source on the model pages.
GPT-5.2 vs GPT-6 Sol: questions
- Is GPT-5.2 better than GPT-6 Sol?
- GPT-6 Sol (max) leads on quality: 67.7 vs 61.4. The BenchLeader Index combines every independent quality benchmark; GPT-6 Sol (max) is ahead overall as of 2026-09-23, but check the category scores for your use.
- Which is cheaper, GPT-5.2 or GPT-6 Sol?
- GPT-6 Sol is cheaper: $4.00 against $4.81 per million tokens, blended at three input tokens per output token.
- Which is faster, GPT-5.2 or GPT-6 Sol?
- GPT-6 Sol streams faster: 126 against 80 output tokens per second.
- Which has the larger context window?
- GPT-6 Sol accepts more context: 1.1M against 400k tokens.