Agnes 2.5 Pro Beta vs GPT-5.5
Agnes 2.5 Pro Beta 
GPT-5.5 Verdict
- GPT-5.5 (xhigh) leads on quality: 67.6 vs 60.8.
- Agnes 2.5 Pro Beta is stronger in agents & tools, composite.
- GPT-5.5 (xhigh) is stronger in knowledge, long context, multimodal, reasoning, coding, instruction following, maths.
- Agnes 2.5 Pro Beta is 75× cheaper ($0.150 vs $11.25 per 1M blended).
| Metric | Agnes 2.5 Pro Beta | GPT-5.5 (xhigh) |
|---|---|---|
| BenchLeader Index | 60.8 | 67.6 |
| Agents & tools score | 64.4 | 62.3 |
| Composite score | 73.7 | 72.5 |
| Knowledge score | 59.2 | 66.4 |
| Long context score | 68.0 | 68.7 |
| Multimodal score | 59.8 | 64.4 |
| Reasoning score | 72.2 | 79.9 |
| Coding score | – | 64.6 |
| Instruction following score | – | 73.8 |
| Maths score | – | 71.2 |
| Blended price $/M | $0.150 | $11.25 |
| Output speed | – | 79 tok/s |
| Time to first answer | – | 52.2 s |
| Context window | 1M | 1.1M |
| FrontierMath Tiers 1–3 | – | 85.3% |
| FrontierMath Tier 4 | – | 72.5% |
| SimpleQA Verified | – | 63.0% |
| OSWorld-Verified 2.0 | – | 13.0% |
| SciCode | – | 56.1% |
| WeirdML | – | 84.9% |
| APEX-Agents | – | 38.5% |
| ProofBench | – | 50.0% |
| GSO-Bench | – | 40.2% |
| LMArena WebDev | – | 1510 |
| LMArena Agent | – | 5 |
| LiveBench | – | 80.2% |
| LiveBench Reasoning | – | 89.7% |
| LiveBench Coding | – | 82.2% |
| LiveBench Agentic Coding | – | 54.0% |
| LiveBench Mathematics | – | 95.9% |
| LiveBench Data Analysis | – | 81.6% |
| LiveBench Language | – | 87.4% |
| LiveBench Instruction Following | – | 70.7% |
| AA Intelligence Index | 35.2 | 38.6 |
| IFBench | – | 75.8% |
| AA-LCR | 83.0% | 84.3% |
| MMMU-Pro | 75.4% | 79.9% |
| AA-Omniscience | -10.5 | 20.5 |
| Terminal-Bench Hard | – | 60.6% |
| GPQA Diamond (AA) | 90.5% | 93.5% |
| Humanity's Last Exam (AA) | 37.5% | 45.8% |
| SciCode (AA) | 48.8% | 55.8% |
| τ²-Bench Telecom (AA) | – | 93.9% |
| LiveCodeBench | – | 85.3% |
| MMLU-Pro | – | 88.1% |
| LegalBench | – | 86.5% |
| CorpFin | – | 68.4% |
| TaxEval | – | 75.0% |
| SWE-bench (Vals) | – | 82.6% |
| GPQA Diamond (Vals) | – | 93.2% |
| Vals Index | – | 57.4 |
| AIME 2026 | – | 100.0% |
| HMMT February 2026 | – | 98.5% |
| MathArena Apex | – | 80.2% |
| MCP Atlas | – | 75.3% |
| ARC-AGI-1 | – | 95.0% |
| ARC-AGI-2 | – | 85.0% |
| CritPt | 15.7% | 27.1% |
| GDPval (AA) | 43.8% | 44.8% |
| τ²-Bench Banking (AA) | 35.7% | 39.0% |
| ITBench SRE (AA) | – | 45.8% |
| Analyst Agent (AA) | – | 50.0% |
| APEX-Agents (AA) | – | 37.7% |
| CaseLaw v2 | – | 66.2% |
| Code Migration | – | 45.2% |
| Excel Modeling Benchmark | – | 64.5% |
| Finance Agent v2 | – | 51.8% |
| Harvey's Legal Agent Benchmark | – | 3.8% |
| Legal Research Bench | – | 40.4% |
| MedCode | – | 49.1% |
| MedScribe | – | 86.9% |
| MMMU-Pro (Vals) | – | 88.3% |
| MortgageTax | – | 68.8% |
| ProgramBench | – | 0.5% |
| Public Benefits Bench | – | 60.9% |
| SAGE | – | 51.5% |
| SkillsBench | – | 62.2% |
| SREBench | – | 3.8% |
| Tax Agent Bench | – | 60.5% |
| Time Horizon Index: KSP | – | 8.3% |
| Vals Multimodal Index | – | 68.1% |
| Vibe Code Bench v1.1 | – | 69.8% |
| DrugDiscoveryBench | – | 51.6% |
| FORTRESS | – | 16.3% |
| SWE Atlas: Codebase QnA | – | 45.4% |
| SWE Atlas: Refactoring | – | 44.8% |
| SWE Atlas: Test Writing | – | 42.6% |
| EBR-bench | – | 34.3% |
| Mystery Game Puzzles | – | 56.0% |
| PostTrainBench | – | 27.2% |
| DeepSWE | – | 67.0% |
| LMCA | – | 54.3% |
| DTBench | – | 96.0% |
| CursorBench | – | 58.4% |
| ALE-Bench | – | 1943.0 |
| GDP.pdf | – | 26.0% |
Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.
Agnes 2.5 Pro Beta vs GPT-5.5: questions
- Is Agnes 2.5 Pro Beta better than GPT-5.5?
- GPT-5.5 (xhigh) leads on quality: 67.6 vs 60.8. The BenchLeader Index combines every independent quality benchmark; GPT-5.5 (xhigh) is ahead overall as of 2026-09-19, but check the category scores for your use.
- Is Agnes 2.5 Pro Beta better than GPT-5.5 for agentic tasks?
- Agnes 2.5 Pro Beta scores higher in agentic tasks (64 vs 62 on the category index, where 50 is average).
- Which is cheaper, Agnes 2.5 Pro Beta or GPT-5.5?
- Agnes 2.5 Pro Beta is cheaper: $0.150 against $11.25 per million tokens, blended at three input tokens per output token.
- Which has the larger context window?
- GPT-5.5 accepts more context: 1.1M against 1M tokens.