- SWE-bench Verified 88.6
- Agentic coding SWE-Bench Pro 69.2
- SWE-bench Multilingual 84.4
- SWE-bench Multimodal 38.4
- BrowseComp (multi-agent) 88.5
- Agentic terminal coding Terminal-Bench 2.1 74.6
- Multidisciplinary reasoning Humanity's Last Exam (with tools) 57.9
- ChartQAPro (with tools) 72.3
- Agentic computer use OSWorld-Verified 83.4
- GPQA Diamond 93.6
- ScreenSpot-Pro (with tools) 87.9
- Agentic financial analysis Finance Agent v2 53.9
- Knowledge work GDPval-AA 1890
- MCP-Atlas 82.2
- Automation Bench 15.5
- Best of GraphWalks BFS 256K / GraphWalks Parents 256K 99.3
Claude Opus 4.8
Claude Opus 4.8 ranks first on 16 of the 248 benchmarks it has scores on.
266
Benchmarks with a score
16
Ranked first, out of five or more models
44
In the top three
Anthropic May 2026
Claude Opus 4.8
Closed weights Flagship
159.6
#17 of 271
Epoch Capabilities Index
- DeepSWE 59% #15 /28
- Terminal-Bench 4.0 23.6% #14 /23
- τ³-bench Banking 39.7% #8 /25
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BullshitBench V2 | 95% | #1 of 122 | Official leaderboard | |
| BullshitBench | 96.4% | #1 of 107 | Official leaderboard | |
| EQ-Bench 3 | 2,058 | #2 of 78 | Official leaderboard | |
| LMArena (Elo) | 1,482 | #22 of 333 | Official leaderboard | |
| INCLUDE | 87.6% | #2 of 25 | Model card | |
| Humanity's Last Exam | 57.9% | #15 of 147 | Model card | |
| Creative Writing v3 | 79.7 | #14 of 120 | Official leaderboard | |
| Longform Creative Writing (EQ-Bench) | 80.8 | #14 of 119 | Official leaderboard | |
| FACTS Search | 80.3% | #4 of 31 | Official leaderboard | |
| GraphWalks | 99.3% | #3 of 21 | Model card | |
| Global MMLU Lite | 94.8% | #7 of 43 | Official leaderboard | |
| SEA-HELM | 75.6 | #11 of 62 | Official leaderboard | |
| Document Arena | 1,486 | #7 of 37 | Official leaderboard | |
| Extended NYT Connections | 91.1% | #20 of 97 | Official leaderboard | |
| Judgemark v4 | 78.0 | #9 of 40 | Official leaderboard | |
| FACTS Benchmark Suite | 59.7% | #11 of 40 | Official leaderboard | |
| EQ-Bench 4 | 1,268 | #9 of 32 | Official leaderboard | |
| ECLeKTic | 39% | #3 of 10 | Model card | |
| SimpleQA Verified | 44.5% | #20 of 56 | Official leaderboard | |
| AA-Omniscience | 37% | #7 of 17 | Model card | |
| Global MMLU | 90.4% | #5 of 11 | Model card | |
| MILU | 90.3% | #5 of 10 | Model card | |
| False-premise questions (Anthropic) | 77% | #3 of 6 | Model card | |
| FACTS Multimodal | 39.8% | #20 of 39 | Official leaderboard | |
| FACTS Search V2 | 79.6% | #13 of 21 | Official leaderboard | |
| FACTS Parametric | 25.1% | #30 of 45 | Official leaderboard | |
| 100Q-Hard (Anthropic) | 20% | #6 of 7 | Model card |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MathArena (Apex, IMO, USAMO) | 81.3% | #1 of 47 | Official leaderboard | |
| xbench-ScienceQA | 76.4% | #1 of 29 | Official leaderboard | |
| AIME 2026 | 100% | #2 of 31 | Official leaderboard | |
| FrontierMath | 47.2% | #5 of 70 | Epoch AI | |
| ProofBench | 69% | #6 of 59 | Official leaderboard | |
| FrontierMath Tier 4 | 31.3% | #6 of 55 | Epoch AI | |
| OTIS Mock AIME 2024-2025 | 98.3% | #25 of 202 | Epoch AI | |
| DTBench | 91.5% | #24 of 178 | Official leaderboard | |
| GPQA Diamond | 91% | #31 of 219 | Epoch AI | |
| CritPt | 20.9% | #26 of 160 | Epoch AI | |
| Surface Evolver Bench | 87.5% | #5 of 26 | Epoch AI | |
| Organic Chemistry (Anthropic) | 86.2% | #1 of 5 | Model card | |
| FrontierMath Tiers 1-3 v2 | 80% | #18 of 89 | Epoch AI | |
| ResearchClawBench | 22.8 | #5 of 23 | Official leaderboard | |
| HMMT 2026 | 95.5% | #7 of 31 | Official leaderboard | |
| SimpleBench | 64.8% | #25 of 100 | Official leaderboard | |
| ARC-AGI-2 | 72.1% | #25 of 95 | Official leaderboard | |
| FrontierMath Tier 4 v2 | 56.1% | #19 of 71 | Epoch AI | |
| ARC-AGI | 92.5% | #27 of 92 | Official leaderboard | |
| BTF-3 | 0.13 | #3 of 10 | Epoch AI | |
| BioPipelineBench (Anthropic) | 87.7% | #1 of 3 | Model card | |
| ForecastBench | 61.6 | #32 of 86 | Official leaderboard | |
| LatchBio Capabilities v1.0 | 45.3% | #11 of 27 | Official leaderboard | |
| Verifying the Verifiers (Project APE CRED benchmark) | 85% | #10 of 23 | Official leaderboard | |
| BixBench3 | 46.0 | #10 of 20 | Official leaderboard | |
| USAMO 2026 | 96.7% | #3 of 6 | Model card | |
| Structural Biology (Anthropic) | 79% | #1 of 2 | Model card | |
| Terminal-Bench-Science | 10.5% | #10 of 17 | Official leaderboard | |
| ArXivMath | 71.8% | #5 of 8 | Model card | |
| scBench (LatchBio SingleCellBench) | 58.2% | #4 of 6 | Model card | |
| ProteinGym | 39.6% | #2 of 3 | Model card | |
| SpatialBench (LatchBio) | 53.3% | #6 of 6 | Model card |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SWE-bench Verified | 88.6% | #4 of 150 | Model card | |
| OpenHands Index | 71.9% | #2 of 33 | Official leaderboard | |
| EvoCode-Bench v2 | 59.1% | #1 of 13 | Official leaderboard | |
| WeirdML | 82.9% | #9 of 112 | Official leaderboard | |
| FrontierCode | 34.3% | #1 of 12 | Official leaderboard | |
| PostTrainBench | 34.1% | #2 of 23 | Official leaderboard | |
| SWE-Bench Pro | 69.2% | #7 of 77 | Model card | |
| SWE-bench Multilingual | 84.4% | #7 of 70 | Model card | |
| GBAEval | 70.9% | #3 of 21 | Official leaderboard | |
| FrontierCS | 74.5 | #2 of 14 | Official leaderboard | |
| GSO-Bench | 47.1% | #5 of 30 | Official leaderboard | |
| Monthly-SWEBench | 69% | #2 of 12 | Official leaderboard | |
| SWE-Marathon | 26% | #2 of 12 | Official leaderboard | |
| SWE Atlas | 57.3% | #4 of 22 | Official leaderboard | |
| ALE-Bench | 1,564 | #23 of 121 | Epoch AI | |
| Vibe Code Bench | 82.7% | #23 of 115 | Official leaderboard | |
| Code Migration | 47.3% | #16 of 78 | Official leaderboard | |
| MirrorCode | 65.6% | #6 of 28 | Epoch AI | |
| TasteVal | 84.2× | #5 of 20 | Official leaderboard | |
| FrontierCode 1.1 | 46.5% | #2 of 8 | Official leaderboard | |
| SWE Atlas Test Writing | 49.6% | #6 of 22 | Official leaderboard | |
| WebDev Arena | 1,559 | #29 of 105 | Epoch AI | |
| SWE Atlas Refactoring | 46.7% | #5 of 17 | Official leaderboard | |
| Senior SWE-Bench | 30.5% | #7 of 23 | Official leaderboard | |
| Code Arena | 1,556 | #39 of 124 | Official leaderboard | |
| PostTrainBench 1.1 | 33.8% | #4 of 11 | Official leaderboard | |
| AndroidBench | 72.4% | #13 of 32 | Official leaderboard | |
| Vals RSI Index | 0.24 | #11 of 25 | Official leaderboard | |
| MLS-Bench | 42.8% | #7 of 15 | Official leaderboard | |
| DeepSWE | 59% | #15 of 28 | Official leaderboard | |
| SWE-bench-Live | 34% | #7 of 13 | Official leaderboard | |
| Vision2Web | 76.1% | #6 of 10 | Official leaderboard | |
| PostTrainBench 1.2 | 31% | #11 of 17 | Official leaderboard | |
| SWE-bench Multimodal | 38.4% | #7 of 10 | Model card | |
| GameDevBench | 55.9% | #8 of 10 | Official leaderboard | |
| ProgramBench | 0% | #21 of 25 | Official leaderboard | |
| FrontierCode 2.0 | 14.7% | #22 of 26 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| PinchBench 2.0 | 93.5% | #1 of 57 | Official leaderboard | |
| SnakeBench | 35 | #8 of 183 | Official leaderboard | |
| GAIA | 88.7% | #3 of 57 | Official leaderboard | |
| ScreenSpot-Pro | 87.9% | #2 of 25 | Model card | |
| UniClawBench | 47.5% | #1 of 10 | Official leaderboard | |
| MyPCBench | 62% | #1 of 9 | Official leaderboard | |
| LisanBench | 9463.0 | #15 of 133 | Official leaderboard | |
| Toolathlon-Verified | 76.2% | #3 of 25 | Official leaderboard | |
| OSWorld-Verified | 83.4% | #5 of 37 | Model card | |
| DeepSearchQA | 93.1% | #3 of 22 | Model card | |
| OSWorld 2.0 | 20.6% | #1 of 7 | Official leaderboard | |
| BrowseComp | 88.5% | #12 of 77 | Model card | |
| Chess Puzzles | 52% | #15 of 83 | Epoch AI | |
| PACT | 1,562 | #5 of 26 | Official leaderboard | |
| Game Arena Nine Men's Morris | 817 | #7 of 36 | Official leaderboard | |
| EdgeBench | 51.3 | #1 of 5 | Official leaderboard | |
| Game Arena Checkers | 1,080 | #8 of 38 | Official leaderboard | |
| CEO-Bench | $2,399,209 | #4 of 19 | Official leaderboard | |
| Harbor-Index | 20.7% | #2 of 9 | Official leaderboard | |
| Long-Horizon-Terminal-Bench (LHTB) | 49.2% | #6 of 25 | Official leaderboard | |
| Game Arena Dots and Boxes | 1,018 | #9 of 37 | Official leaderboard | |
| DeepResearch Bench | 50.2% | #6 of 24 | Epoch AI | |
| OSWorld 2.1 | 44.4% | #1 of 4 | Official leaderboard | |
| Mystery Game Puzzles | 36% | #21 of 80 | Epoch AI | |
| Game Arena Ultimate Tic-Tac-Toe | 426 | #10 of 36 | Official leaderboard | |
| SkillsBench | 54.1% | #6 of 21 | Official leaderboard | |
| MCP Atlas | 82.2% | #10 of 34 | Official leaderboard | |
| Toolathlon | 59.9% | #11 of 37 | Model card | |
| Game Arena Go | 1,097 | #11 of 36 | Official leaderboard | |
| τ³-bench Banking | 39.7% | #8 of 25 | Official leaderboard | |
| LLM Chess | 450 | #41 of 124 | Official leaderboard | |
| OSWorld 2.0 (Aug 2026) | 37.6% | #1 of 3 | Official leaderboard | |
| Terminal-Bench 2.1 | 78.9% | #5 of 13 | Official leaderboard | |
| Game Arena Four in a Row | 423 | #15 of 38 | Official leaderboard | |
| Kaggle Game Arena | 321 | #17 of 39 | Official leaderboard | |
| Game Arena Dark Hex | 258 | #17 of 38 | Official leaderboard | |
| Game Arena Clobber | 303 | #17 of 36 | Official leaderboard | |
| Game Arena Lines of Action | 522 | #17 of 36 | Official leaderboard | |
| LiveClawBench | 68.8% | #9 of 17 | Official leaderboard | |
| EBR-bench | 28.6% | #15 of 28 | Epoch AI | |
| ARC-AGI-3 | 1.52% | #13 of 24 | Official leaderboard | |
| Game Arena Coin Game | 350 | #19 of 35 | Official leaderboard | |
| Game Arena Word Art | 367 | #19 of 35 | Official leaderboard | |
| Terminal-Bench 3.0 | 21.1% | #6 of 11 | Official leaderboard | |
| Game Arena Five in a Row | 452 | #11 of 20 | Official leaderboard | |
| LMArena Search Arena | 1,195 | #20 of 35 | Official leaderboard | |
| Game Arena Bargaining | 178 | #21 of 36 | Official leaderboard | |
| Game Arena Reversi | 381 | #21 of 36 | Official leaderboard | |
| Terminal-Bench 4.0 | 23.6% | #14 of 23 | Official leaderboard | |
| Time Horizon Index: KSP | 11.8% | #8 of 13 | Official leaderboard | |
| Game Arena Word Association | 166 | #24 of 36 | Official leaderboard | |
| Game Arena Poker | -6.35 | #21 of 31 | Official leaderboard | |
| Game Arena Chess | 622 | #27 of 39 | Official leaderboard | |
| RecreationBench | 31.1% | #7 of 10 | Official leaderboard | |
| DRACO | 80.4% | #8 of 11 | Model card | |
| AutomationBench | 15.5% | #38 of 41 | Model card |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MortgageTax | 69.9% | #5 of 86 | Official leaderboard | |
| MedCode | 53.2% | #10 of 96 | Official leaderboard | |
| TaxEval v2 | 75.6% | #14 of 129 | Official leaderboard | |
| GDPval-AA | 1,890 | #2 of 16 | Model card | |
| FORTE | 77.2% | #3 of 21 | Official leaderboard | |
| CorpFin v2 | 66.7% | #18 of 119 | Official leaderboard | |
| CommerceAgentBench | 55.1% | #2 of 13 | Official leaderboard | |
| ProfBench | 56.8% | #13 of 72 | Official leaderboard | |
| Excel Modeling Benchmark | 69.4% | #15 of 76 | Official leaderboard | |
| E-Commerce Bench | 4.98 | #4 of 19 | Official leaderboard | |
| Harvey LAB (Legal Agent Benchmark) | 9.58% | #20 of 80 | Official leaderboard | |
| MedScribe | 85.8% | #25 of 98 | Official leaderboard | |
| Public Benefits Bench | 68.1% | #13 of 50 | Official leaderboard | |
| Legal Research Bench | 43.8% | #23 of 88 | Official leaderboard | |
| Remote Labor Index | 8.33% | #6 of 17 | Official leaderboard | |
| Vals Finance Agent v2 | 53.9% | #29 of 80 | Official leaderboard | |
| Vending-Bench Arena | $6,196 | #12 of 32 | Official leaderboard | |
| JobBench | 48.4% | #6 of 16 | Official leaderboard | |
| LegalBench | 83.6% | #53 of 138 | Official leaderboard | |
| Tax Agent Bench | 30% | #31 of 79 | Official leaderboard | |
| Vending-Bench 2 | $5,787 | #26 of 66 | Official leaderboard | |
| OfficeQA | 77.6% | #5 of 12 | Model card | |
| CADGenBench | 34.5% | #5 of 11 | Official leaderboard | |
| prinzbench | 42.0 | #12 of 26 | Official leaderboard | |
| OfficeQA Pro | 66.2% | #7 of 14 | Model card | |
| TaxCalcBench v2 | 36% | #14 of 26 | Official leaderboard | |
| BlenderWorld | 57.0 | #7 of 13 | Official leaderboard | |
| APEX-Agents | 48.9% | #31 of 56 | Epoch AI | |
| EEBench | 51.4% | #15 of 26 | Official leaderboard | |
| FrontierFinance | 45% | #11 of 16 | Official leaderboard | |
| HealthBench Professional | 55.8% | #21 of 25 | Model card | |
| PolicyBench | 75.8% | #43 of 50 | Official leaderboard | |
| RedlineBench | 44.4% | #4 of 4 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vision Arena | 1,286 | #17 of 136 | Official leaderboard | |
| ChartQA Pro | 72.3% | #1 of 8 | Model card | |
| ChartMuseum | 75.8% | #1 of 5 | Model card | |
| BabyVision | 81.2% | #6 of 27 | Official leaderboard | |
| ZeroBench | 18% | #16 of 66 | Official leaderboard | |
| GeoBench | 81% | #14 of 48 | Official leaderboard | |
| Drone-Bench | 82.3% | #6 of 19 | Official leaderboard | |
| LongExtractionBench | 70.7% | #1 of 3 | Official leaderboard | |
| GDP.pdf | 24% | #14 of 39 | Epoch AI | |
| Math Kangaroo 2025 (MathArena) | 81.6% | #10 of 22 | Official leaderboard | |
| Furniture Assembly Benchmark | 42.5% | #16 of 35 | Epoch AI | |
| CharXiv | 80.5% | #32 of 67 | Model card | |
| VoxelBench | 1,632 | #32 of 56 | Official leaderboard | |
| ParseBench | 62.3% | #24 of 42 | Official leaderboard | |
| 1H-VideoQA | 71.3% | #12 of 20 | Official leaderboard | |
| Blueprint-Bench 2 | 14.5% | #28 of 35 | Official leaderboard | |
| Humanity's Sixth Sense | 23.5% | #26 of 29 | Official leaderboard | |
| ArtifactArena | 929 | #19 of 21 | Official leaderboard | |
| EnigmaEval | 23.5% | #5 of 5 | Official leaderboard |
Safety and security
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SAGE (Vals) | 54.8% | #3 of 81 | Official leaderboard | |
| LMCA | 57.5% | #11 of 139 | Epoch AI | |
| Conceptual Reasoning Index | 68.3 | #12 of 149 | Official leaderboard | |
| ACCoRD | 77.4 | #19 of 150 | Official leaderboard | |
| Vals Multimodal Index | 70.9% | #5 of 33 | Official leaderboard | |
| CAIS Risk Index | 38.1 | #11 of 65 | Official leaderboard | |
| CAIS Text Capabilities Index | 41.2 | #17 of 66 | Official leaderboard | |
| CAIS Vision Capabilities Index | 53.0 | #25 of 53 | Official leaderboard | |
| Anthropic ECI (AECI) | 155.5 | #5 of 6 | Model card |
Anthropic's models over time
Anthropic's models in color, against every other model on the Epoch Capabilities Index, by release date.
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it. 81 of them aren't in the launch post.
System Card: Claude Opus 4.8 28 May 2026
Capabilities
- SWE-bench Verified 88.6
- SWE-Bench Pro 69.2
- SWE-bench Multilingual 84.4
- SWE-bench Multimodal 38.4
- BrowseComp 84.3
- Terminal-Bench 2.1 74.6
- Humanity's Last Exam 49.8
- ChartQA Pro 69.4
- OSWorld-Verified 83.4
- GPQA Diamond 93.6
- ScreenSpot-Pro 82.3
- Vals Finance Agent v2 53.9
- GDPval-AA 1890
- MCP Atlas 82.2
- AutomationBench 15.5
- GraphWalks
- FrontierSWE v1
- ProgramBench 79
- USAMO 2026 96.7
- ArXivMath 71.8
- DeepSearchQA 93.1
- DRACO 80.4
- ChartMuseum 75.8
- LAB-Bench FigQA 80.4
- CharXiv 80.5
- OfficeQA 77.6
- OfficeQA Pro 66.2
- Harvey LAB (Legal Agent Benchmark) 9.62
- Vending-Bench 2 2992.3
- Toolathlon 59.9
- Global MMLU 90.4
- MILU 90.3
- INCLUDE 87.6
- BioPipelineBench (Anthropic) 87.7
- BioMysteryBench
- SpatialBench (LatchBio) 53.3
- scBench (LatchBio SingleCellBench) 58.2
- Structural Biology (Anthropic) 79
- ProteinGym 39.6
- Organic Chemistry (Anthropic) 86.2
- Protocols (Anthropic life sciences) 59.6
- LABBench2
Health
Hallucination
Safety
- Single-turn harmful request evaluations (Anthropic) 98
- Single-turn benign request evaluations (Anthropic) 0.36
- Multi-turn testing (Anthropic)
- Child safety evaluations (Anthropic)
- Suicide and self-harm evaluations (Anthropic)
- Disordered eating evaluations (Anthropic)
- Election integrity evaluations (Anthropic)
- Malicious use of Claude Code (Anthropic) 95.1
- Malicious computer use (Anthropic) 81.7
Robustness
- Gray Swan Agent Red Teaming (ART) benchmark 0.1
- Prompt injection live bug bounty (Anthropic with Gray Swan) 0.4
- Prompt injection robustness against adaptive attackers, coding (Anthropic) 7.03
- Prompt injection robustness against adaptive attackers, computer use (Anthropic) 7.14
- Prompt injection robustness against adaptive attackers, browser use (Anthropic) 31.5
Alignment
- Anthropic automated behavioral audit
- Petri
- Evaluation awareness discriminability (Anthropic)
- UK AISI unprompted sabotage evaluation 0
- UK AISI sabotage continuation evaluation 1
- Over-eager behavior on GUI computer use tasks (Anthropic) 9.4
- Adherence to its constitution (Anthropic) 0.99
- MASK 95.4
- Lying about identity (Anthropic) 97
- Refusal to assist with AI safety R&D (Anthropic)
- Self-preference bias (Anthropic)
- Uncritically reporting flawed results (Anthropic) 9.4
- Code summary honesty (Anthropic) 3.7
- Lazy investigation on misleading codebases (Anthropic) 0
- Overconfidence: verifying command-line syntax (Anthropic) 4.51
Monitorability
Bio and chem risk
Cyber risk
AI R&D risk
- Anthropic ECI (AECI) 155.5