Agnes 2.5 Pro Beta vs Claude Opus 5
Full profiles: Agnes 2.5 Pro Beta (Sapiens AI) and Claude Opus 5 (Anthropic): every benchmark, price and rank.
Updated · Data from 12 sources
As of 16 Nov 2026, there are not enough shared benchmarks for a verdict, and Agnes 2.5 Pro Beta is 67× cheaper at $0.150 vs $10.00 per 1M tokens blended. Choose Agnes 2.5 Pro Beta for long context (66 vs 64); choose Claude Opus 5 for multimodal (67 vs 58).
Key facts (as of 16 Nov 2026)
- Agnes 2.5 Pro Beta costs $0.150 per 1M tokens blended (list price, 16 Nov 2026).
- Claude Opus 5 costs $10.00 per 1M tokens blended (list price, 16 Nov 2026).
- Of the 10 benchmarks both models have, Claude Opus 5 leads 9 (BenchLeader, 16 Nov 2026).
Which to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Agents & tool use | Either | 64 vs 64 category score; τ³-Banking (AA) 35.7% vs 42.1% | Either |
| Long documents | Agnes 2.5 Pro Beta | 66 vs 64 category score; AA-LCR v1.1 83.0% vs 79.3% | Medium |
| Images and other media | Claude Opus 5 | 67 vs 58 category score; MMMU-Pro 84.7% vs 75.4% | High |
| Chat quality (human preference) | – | Only Claude Opus 5 has an Arena rating (68 category score) | Not comparable |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Not enough shared benchmarks for a verdict.
- Agnes 2.5 Pro Beta is stronger in agents & tools, long context.
- Claude Opus 5 (max) is stronger in multimodal.
- Agnes 2.5 Pro Beta is 67× cheaper ($0.150 vs $10.00 per 1M blended).
At a glance
| Spec | Agnes 2.5 Pro Beta | Claude Opus 5 |
|---|---|---|
| Developer | Sapiens AI | Anthropic |
| Released | 26 Aug 2026 | 24 Jul 2026 |
| Context window (tokens) | 1,000,000 | 1,000,000 |
| Compared at | Agnes 2.5 Pro Beta | Claude Opus 5 (max) |
| Open weights | No | No |
| Price in / out / cached input per 1M | – | $5.00 / $25.00 / $0.500 |
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | Agnes 2.5 Pro Beta | Claude Opus 5 (max) | Leader |
|---|---|---|---|
| Reasoning | – | 66.1 | not comparable |
| Coding | – | 67.0 | not comparable |
| Agents & tools | 64.4 | 63.8 | level |
| Maths | – | 69.8 | not comparable |
| Knowledge | – | 65.2 | not comparable |
| Human preference | – | 68.1 | not comparable |
| Multimodal | 57.7 | 67.2 | Claude Opus 5 |
| Long context | 66.2 | 64.3 | Agnes 2.5 Pro Beta |
On one chart
Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.
Not drawn, measured for fewer than two of these models: Reasoning, Coding, Maths, Knowledge, Instruction following, Human preference.
Where sources disagree
Across the 10 benchmarks both have, Agnes 2.5 Pro Beta leads 1, Claude Opus 5 leads 9.
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | Agnes 2.5 Pro Beta | Claude Opus 5 (max) |
|---|---|---|
| Blended price per 1M tokens | – | $10.00 |
| Input / output per 1M | – / – | $5.00 / $25.00 |
| Cached input per 1M | – | $0.500 |
| Price per task: chat reply | – | $0.0095 |
| Price per task: summarize a 30-page report | – | $0.075 |
| Price per task: code edit | – | $0.068 |
| Price per task: agentic coding session | – | $0.400 |
| Price per task: structured extraction | – | $0.015 |
| Agentic coding session, input mostly cached | – | $0.198 |
| Cost per benchmark task (AA Index) | – | $11.82 |
| Output tokens per task (AA Index) | – | 118k |
| Of which reasoning | – | 73k |
| Time per task (AA Index) | – | 25 min |
| Output speed | – | 80 tok/s |
| Time to first answer | – | 48.5 s |
| Time to a complete answer, last measured 13 Nov 2026 | – | 191.6 s |
Each model is compared at its best-ranked reasoning-effort setting. Agnes 2.5 Pro Beta. Claude Opus 5 (max) scores 65.0 and takes 49 s to its first answer token; Claude Opus 5 (high) scores 64.4 in 17 s, Claude Opus 5 scores 63.2 in 2 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
144 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | Agnes 2.5 Pro Beta | Claude Opus 5 (max) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | – | 65.0 |
| Agents & tools score | BenchLeader | 64.4 | 63.8 |
| Long context score | BenchLeader | 66.2 | 64.3 |
| Multimodal score | BenchLeader | 57.7 | 67.2 |
| Coding score | BenchLeader | – | 67.0 |
| Human preference score | BenchLeader | – | 68.1 |
| Knowledge score | BenchLeader | – | 65.2 |
| Maths score | BenchLeader | – | 69.8 |
| Reasoning score | BenchLeader | – | 66.1 |
| Blended price $/M | BenchLeader | – | $10.00 |
| Output speed | BenchLeader | – | 80 tok/s |
| Time to first answer | BenchLeader | – | 48.5 s |
| Context window | BenchLeader | 1,000,000 tokens | 1,000,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | – | 93.9% |
| SimpleBench | SimpleBench | – | 80.6%† |
| Arena Hard Prompts | Arena (LMArena) | – | 1513 |
| LiveBench 1.0 Reasoning | LiveBench | – | 91.2% |
| GPQA Diamond (AA) | Artificial Analysis | 90.5% | 93.2% |
| Humanity's Last Exam (AA) | Artificial Analysis | 37.5% | 54.9% |
| HLE-Diamond (AA) | Artificial Analysis | – | 44.8% |
| GPQA Diamond (Vals) | Vals AI | – | 93.4%† |
| ARC-AGI-1 | ARC Prize | – | 97.5% |
| ARC-AGI-2 | ARC Prize | – | 90.4% |
| ARC-AGI-3 | ARC Prize | – | 30.2%† |
| CritPt | Artificial Analysis | 15.7% | 29.1% |
| CritPt v2 hard subset (AA) | Artificial Analysis | – | 50.0% |
| MysteryMechanism | Vals AI | – | 37.4% |
| HLE-Diamond (Scale) | Scale AI SEAL | – | 38.6%† |
| Arena Expert | Arena (LMArena) | – | 1530 |
| Chess Puzzles | Epoch AI Benchmarking Hub | – | 43.0% |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | – | 59.0% |
| LMCA | Epoch AI Benchmarking Hub | – | 63.3% |
| DTBench | Epoch AI Benchmarking Hub | – | 97.6% |
| ForecastBench | ForecastBench | – | 66.6% |
| BTF-3 | Epoch AI Benchmarking Hub | – | 12.0%† |
| Coding | |||
| SciCode | SciCode | – | 56.4% |
| WeirdML | WeirdML | – | 91.8% |
| FrontierCode | Cognition | – | 53.4% |
Show all 144 benchmarks
| Metric | Publisher | Agnes 2.5 Pro Beta | Claude Opus 5 (max) |
|---|---|---|---|
| Coding | |||
| Arena Coding | Arena (LMArena) | – | 1528 |
| Arena WebDev | Arena (LMArena) | – | 1691 |
| LiveBench 1.0 Coding | LiveBench | – | 81.5% |
| SciCode (AA) | Artificial Analysis | 48.8% | 56.4% |
| LiveCodeBench | Vals AI | – | 89.0% |
| IOI | Vals AI | – | 84.3% |
| SWE-bench (Vals) | Vals AI | – | 97.0%† |
| Code Migration | Vals AI | – | 57.5% |
| ProgramBench | Vals AI | – | 3.0% |
| Vibe Code Bench 1-100 | Vals AI | – | 28.5% |
| Vibe Code Bench v1.1 | Vals AI | – | 88.4%† |
| SWE Atlas v1.0: Codebase QnA | Scale AI SEAL | – | 63.2%† |
| SWE Atlas v1.0: Test Writing | Scale AI SEAL | – | 62.2%† |
| SWE-Bench Pro V2 | Scale AI SEAL | – | 99.4%† |
| SWE-Bench Pro V2 HARD | Scale AI SEAL | – | 98.0%† |
| MirrorCode | Epoch AI Benchmarking Hub | – | 87.8% |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | – | 73.7% |
| CursorBench | Cursor | – | 46.6% |
| ALE-Bench | Epoch AI Benchmarking Hub | – | 2164.6† |
| FrontierSWE | Epoch AI Benchmarking Hub | – | 52.0% |
| WeirdML v3 | WeirdML | – | 19.0%† |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | – | 49.0% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 69.7% | 89.1% |
| Startrise Frontend | Startrise | – | 82.3%† |
| GameBench 2 Overall | DuelLab GameBench 2 | – | 76.5† |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | – | 84.8† |
| Design Arena Website | Design Arena | – | 1304† |
| FrontierCode 2.0 (AA) | Artificial Analysis | – | 31.1% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | – | 52.1% |
| OSWorld-Verified 2.0 | OSWorld | – | 31.4% |
| APEX-Agents | Mercor | – | 65.8% |
| Arena Agent | Arena (LMArena) | – | 7.2 |
| LiveBench Agentic Coding | LiveBench | – | 65.2% |
| Terminal-Bench 2.1 (Vals) | Vals AI | – | 84.6%† |
| MCP Atlas | Scale AI SEAL | – | 85.8%† |
| HiL-Bench | Scale AI SEAL | – | 57.0%† |
| τ³-bench Banking | τ²-bench | – | 48.7% |
| GDPval-AA v2.1, normalised score | Artificial Analysis | 41.5% | – |
| GDPval-AA v2.1 | Artificial Analysis | 1335 | 1729 |
| τ³-Banking (AA) | Artificial Analysis | 35.7% | 42.1% |
| Analyst Agent (AA) | Artificial Analysis | – | 53.8% |
| CUA-bench | Vals AI | – | 9.0% |
| CyberBench | Vals AI | – | 65.4% |
| Finance Agent v2 | Vals AI | – | 58.6% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | – | 6.7% |
| Legal Research Bench | Vals AI | – | 55.3% |
| SkillsBench | Vals AI | – | 60.4% |
| SREBench | Vals AI | – | 12.2% |
| Tax Agent Bench | Vals AI | – | 47.1% |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 53.5% |
| Terminal-Bench Science | Vals AI | – | 27.1% |
| Time Horizon Index: KSP | Vals AI | – | 18.8% |
| Arena Search | Arena (LMArena) | – | 1213† |
| Arena Agent Task Completion | Arena (LMArena) | – | 10.2 |
| BALROG | BALROG | – | 63.4% |
| PostTrainBench | Epoch AI Benchmarking Hub | – | 35.7%† |
| GBAEval | Epoch AI Benchmarking Hub | – | 79.6%† |
| Vending-Bench 2 | Andon Labs | – | 11181.9† |
| AutomationBench | Artificial Analysis | – | 56.6% |
| GDP.pdf (AA) | Artificial Analysis | – | 21.6% |
| EnterpriseOps-Gym | Artificial Analysis | – | 47.5% |
| AA-Briefcase v1.1 | Artificial Analysis | – | 1654 |
| Design Arena Agentic | Design Arena | – | 1270† |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | – | 28.6% |
| DeepSec-Bench (AA) | Artificial Analysis | – | 25.9% |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | – | 85.6% |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | – | 73.2% |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | – | 98.9% |
| ProofBench | Vals AI | – | 99.0% |
| LiveBench Mathematics | LiveBench | – | 95.7% |
| Arena Maths | Arena (LMArena) | – | 1515 |
| FrontierMath Erdős | Epoch AI Benchmarking Hub | – | 0.0% |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | – | 59.9% |
| LiveBench 1.0 Data Analysis | LiveBench | – | 74.5% |
| AA-Omniscience v1.1 | Artificial Analysis | – | 37.6 |
| MMLU-Pro | Vals AI | – | 91.6% |
| LegalBench | Vals AI | – | 87.0% |
| CorpFin | Vals AI | – | 73.2%† |
| TaxEval | Vals AI | – | 75.1%† |
| BioMysteryBench | Vals AI | – | 79.3% |
| Excel Modeling Benchmark | Vals AI | – | 73.6% |
| MedCode | Vals AI | – | 63.6% |
| MedScribe | Vals AI | – | 91.0% |
| Public Benefits Bench v1.1 | Vals AI | – | 76.9% |
| DrugDiscoveryBench | Scale AI SEAL | – | 53.7% |
| EBR-bench | Epoch AI Benchmarking Hub | – | 45.7% |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 24.0% |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | – | 60.9% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | – | 40.6% |
| FACTS Parametric | – | 48.8%† | |
| Instruction following | |||
| LiveBench Language | LiveBench | – | 88.7% |
| LiveBench Instruction Following | LiveBench | – | 63.8% |
| Arena Instruction Following | Arena (LMArena) | – | 1494 |
| Human preference | |||
| Arena Text | Arena (LMArena) | – | 1489 |
| EQ-Bench 4 | EQ-Bench | – | 1365† |
| EQ-Bench Creative Writing v3 | EQ-Bench | – | 2135† |
| Arena Creative Writing | Arena (LMArena) | – | 1473 |
| Arena Multi-turn | Arena (LMArena) | – | 1486 |
| Arena Longer Queries | Arena (LMArena) | – | 1502 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | – | 1318† |
| MMMU-Pro | Artificial Analysis | 75.4% | 84.7% |
| MMMU-Pro (Vals) | Vals AI | – | 89.9% |
| MortgageTax | Vals AI | – | 72.1%† |
| Humanity's Sixth Sense | Scale AI SEAL | – | 30.5% |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | – | 30.4%† |
| Furniture Assembly | Epoch AI Benchmarking Hub | – | 60.8% |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 83.0% | 79.3% |
| Arena Document | Arena (LMArena) | – | 1486† |
| MLCR | Artificial Analysis | – | 11.1% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | – | 164.7† |
| LiveBench 1.0 | LiveBench | – | 80.1% |
| AA Intelligence Index v5.0.1 | Artificial Analysis | – | 44.2 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 35.2 | 50.8 |
| AA Progress Index v1 | Artificial Analysis | 299.1 | 333.7 |
| Vals RSI Index | Vals AI | – | 33.0% |
| Vals Science Index | Vals AI | – | 47.9% |
| Vals Multimodal Index | Vals AI | – | 73.9%† |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | – | 16.8%† |
| DistressBench | Scale AI SEAL | – | 70.2%† |
Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- Claude Opus 5 (max): 25 new results (LiveCodeBench, MMLU-Pro, IOI…).
- Claude Opus 5 (max): 1 new result (GDPval-AA v2.1).
- Claude Opus 5 (max): 1 new result (MirrorCode).
- Claude Opus 5 (max): BenchLeader Index 65.5 → 65.0.
- Claude Opus 5 (max): 7 new results (AA Intelligence Index v5.0.1, HLE-Diamond (AA), AA-Omniscience v1.1…).
- Claude Opus 5 (max): 1 new result (MirrorCode).
- Claude Opus 5 (max): 1 score revision.
- Claude Opus 5 (max): BenchLeader Index 66.3 → 65.5.
- Agnes 2.5 Pro Beta: 1 new result (AA Progress Index v1).
- Claude Opus 5 (max): 1 new result (AA Progress Index v1).
Related comparisons
- Claude Opus 5 vs Claude Fable 5.2
- Claude Opus 5 vs Gemini 4 Carbon
- Claude Opus 5 vs Claude Opus 5.5
- Claude Opus 5 vs GPT-6 Astra
- Agnes 2.5 Pro Beta vs GPT-6 Sol
- Agnes 2.5 Pro Beta vs Muse Wonder Full
- Agnes 2.5 Pro Beta vs Muse Spark 1.3
- Agnes 2.5 Pro Beta vs Kimi K3
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Agnes 2.5 Pro Beta vs Claude Opus 5: questions
- Agnes 2.5 Pro Beta vs Claude Opus 5: which is cheaper, and will that change?
- Agnes 2.5 Pro Beta is cheaper today: $0.150 against $10.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Agnes 2.5 Pro Beta or Claude Opus 5 better for agents and tool use?
- They are level in agentic tasks (64 vs 64 on the category index). On τ³-Banking (AA), the top shared agents & tools benchmark, it is 35.7% for Agnes 2.5 Pro Beta against 42.1% for Claude Opus 5.
- Which is better for long documents?
- Agnes 2.5 Pro Beta scores higher on long-context benchmarks (66 vs 64). Both accept 1,000,000 tokens of context.
- Do independent benchmarks agree on Agnes 2.5 Pro Beta vs Claude Opus 5?
- Across the 10 benchmarks both have, Agnes 2.5 Pro Beta leads 1, Claude Opus 5 leads 9.
- When was Agnes 2.5 Pro Beta released?
- Agnes 2.5 Pro Beta was released on 26 Aug 2026.