# Claude Opus 4.5 Benchmark Scores & Performance

> Claude Opus 4.5 by Anthropic scores 54.05/100 overall, ranking #77 out of 954 AI models.

Canonical page: https://benchlm.ai/models/claude-opus-4-5

Last updated: October 17, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Anthropic |
| Source Type | Proprietary |
| Reasoning Type | Non-Reasoning |
| Context Window | 200K |
| Overall Score | 54.05/100 |
| Overall Rank | #77 of 954 |

## Family & Coverage

- Family: Claude Opus 4.5
- Variant: base
- Benchmarks covered: 74 of 639
- Sibling models: [Claude Opus 4.5 Thinking](/models/claude-opus-4-5-thinking)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [Terminal-Bench 2.0](/benchmarks/terminal-bench-2) | 59.3% | [Anthropic: Claude Opus 4.5 system card](https://www-cdn.anthropic.com/bf10f64990cfda0ba858290be7b8cc6317685f47.pdf) |
| [OSWorld-Verified](/benchmarks/osworld-verified) | 66.3% | [Anthropic: Claude Opus 4.5 system card](https://www-cdn.anthropic.com/bf10f64990cfda0ba858290be7b8cc6317685f47.pdf) |
| [OSWorld](/benchmarks/osworld) | 66.3% | [Anthropic: Claude Opus 4.5 system card](https://www-cdn.anthropic.com/bf10f64990cfda0ba858290be7b8cc6317685f47.pdf) |
| [Claw-Eval](/benchmarks/claw-eval) | 59.6% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [QwenClawBench](/benchmarks/qwenclawbench) | 52.3% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [τ³-bench results](/benchmarks/tau3-bench) | 70.2% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [VITA-Bench](/benchmarks/vitabench) | 23.3% | [VitaBench leaderboard](https://vitabench.github.io/) |
| [DeepPlanning](/benchmarks/deepplanning) | 26.4% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [Toolathlon](/benchmarks/toolathlon) | 43.5% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [MCP Atlas](/benchmarks/mcpatlas) | 42.3% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [MCP-Tasks](/benchmarks/mcptasks) | 71.8% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [WideResearch](/benchmarks/wideresearch) | 76.4% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [CyberGym](/benchmarks/cybergym) | 50.6% | [CyberGym leaderboard](https://cybergym.io/) |
| [τ²-bench results](/benchmarks/tau2-bench) | 86.3% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/claude-opus-4-5) |
| [Gert Labs](/benchmarks/gertlabs) | 64.23% | [Gert Labs rankings](https://gertlabs.com/rankings) |
| [JobBench](/benchmarks/jobbench) | 32.3% | [JobBench paper](https://arxiv.org/abs/2605.26329) |

## Coding Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [SWE-bench Verified](/benchmarks/swe-bench-verified) | 80.9% | [Anthropic: Claude Opus 4.5 system card](https://www-cdn.anthropic.com/bf10f64990cfda0ba858290be7b8cc6317685f47.pdf) |
| [LiveCodeBench v6](/benchmarks/livecodebench-v6) | 84.8% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [SWE-bench Pro](/benchmarks/swe-bench-pro) | 57.1% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [SWE Multilingual](/benchmarks/swe-bench-multilingual) | 77.5% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [NL2Repo](/benchmarks/nl2repo) | 43.2% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [Terminal-Bench 2.0](/benchmarks/terminal-bench-2) | 59.3% | [Anthropic: Claude Opus 4.5 system card](https://www-cdn.anthropic.com/bf10f64990cfda0ba858290be7b8cc6317685f47.pdf) |

## Multimodal & Grounded Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [MMMU](/benchmarks/mmmu) | 80.7% | [Qwen3.5-397B-A17B model card comparison table](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [MMMU-Pro](/benchmarks/mmmu-pro) | 70.6% | [Qwen3.6-Plus multimodal comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [RealWorldQA](/benchmarks/realworldqa) | 77.0% | [Qwen3.5-397B-A17B model card comparison table](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [OmniDocBench 1.5](/benchmarks/omnidocbench15) | 87.7% | [Qwen3.5-397B-A17B model card comparison table](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [Video-MME (with subtitle)](/benchmarks/videommewithsub) | 77.6% | [Qwen3.5-397B-A17B model card comparison table](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [Video-MME (w/o subtitle)](/benchmarks/videommenosub) | 81.4% | [Qwen3.5-397B-A17B model card comparison table](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [MathVision](/benchmarks/mathvision) | 74.3% | [Qwen3.6-Plus multimodal comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [We-Math](/benchmarks/wemath) | 70.0% | [Qwen3.5-397B-A17B model card comparison table](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [DynaMath](/benchmarks/dynamath) | 79.7% | [Qwen3.5-397B-A17B model card comparison table](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [SimpleVQA](/benchmarks/simplevqa) | 65.7% | [Qwen3.5-397B-A17B model card comparison table](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [CharXiv](/benchmarks/charxiv) | 68.5% | [Qwen3.6-Plus multimodal comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [CountBench](/benchmarks/countbench) | 90.6% | [Qwen3.5-397B-A17B model card comparison table](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [AI2D_TEST](/benchmarks/ai2dtest) | 87.7% | [Qwen3.5-397B-A17B model card comparison table](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [ERQA](/benchmarks/erqa) | 46.8% | [Qwen3.5-397B-A17B model card comparison table](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [VideoMMMU](/benchmarks/videommmu) | 84.4% | [Qwen3.6-Plus multimodal comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [MLVU (M-Avg)](/benchmarks/mlvuavg) | 81.7% | [Qwen3.5-397B-A17B model card comparison table](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [ScreenSpot Pro](/benchmarks/screenspot-pro) | 45.7% | [Qwen3.6-Plus multimodal comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [V*](/benchmarks/vstar) | 67.0% | [Qwen3.6-Plus multimodal comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [AA-MMMU-Pro](/benchmarks/mmmu-pro) | 71.2% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/claude-opus-4-5) |
| [Design Arena Website](/benchmarks/designarenawebsite) | 1248 | [OpenRouter model benchmarks](https://openrouter.ai/anthropic/claude-opus-4.5/benchmarks) |

## Reasoning Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [LongBench v2](/benchmarks/longbench-v2) | 64.4% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [AI-Needle](/benchmarks/aineedle) | 74% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [AA-LCR](/benchmarks/lcr) | 70.7% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/claude-opus-4-5) |
| [CritPt](/benchmarks/critpt) | 0.3% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/claude-opus-4-5) |

## Knowledge Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [GPQA](/benchmarks/gpqa) | 87% | [Anthropic: Claude Opus 4.5 system card](https://www-cdn.anthropic.com/bf10f64990cfda0ba858290be7b8cc6317685f47.pdf) |
| [SuperGPQA](/benchmarks/supergpqa) | 70.6% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [MMLU-Pro](/benchmarks/mmlu-pro) | 89.5% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [MMLU-Redux](/benchmarks/mmluredux) | 96.6% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [C-Eval](/benchmarks/ceval) | 92.2% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [HLE](/benchmarks/hle) | 30.8% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 23.7% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/claude-opus-4-5) |
| [AA-GPQA Diamond](/benchmarks/gpqa-diamond) | 81.0% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/claude-opus-4-5) |
| [AA-HLE](/benchmarks/aahle) | 13.2% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/claude-opus-4-5) |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -4.1% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/claude-opus-4-5) |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 40.9% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/claude-opus-4-5) |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 76.2% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/claude-opus-4-5) |
| [AA MMLU-Pro](/benchmarks/mmlu-pro) | 88.9% | [Artificial Analysis: mmlu-pro leaderboard](https://artificialanalysis.ai/evaluations/mmlu-pro) |

## Instruction Following Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [IFEval](/benchmarks/ifeval) | 90.9% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [IFBench](/benchmarks/ifbench) | 58% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [AA-IFBench](/benchmarks/ifbench) | 43.0% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/claude-opus-4-5) |

## Multilingual Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [MMLU-ProX](/benchmarks/mmluprox) | 85.7% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [NOVA-63](/benchmarks/nova63) | 56.7% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [INCLUDE](/benchmarks/include) | 86.2% | [Qwen3.5-397B-A17B model card comparison table](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [PolyMath](/benchmarks/polymath) | 79.0% | [Qwen3.5-397B-A17B model card comparison table](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |
| [MAXIFE](/benchmarks/maxife) | 79.2% | [Qwen3.5-397B-A17B model card comparison table](https://huggingface.co/Qwen/Qwen3.5-397B-A17B) |

## Mathematics Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AIME26](/benchmarks/aime2026) | 95.1% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [HMMT Feb 2025](/benchmarks/hmmtfeb2025) | 92.9% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [HMMT Nov 2025](/benchmarks/hmmtnov2025) | 93.3% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [HMMT Feb 2026](/benchmarks/hmmtfeb2026) | 85.3% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [MMAnswerBench](/benchmarks/mmanswerbench) | 84.0% | [Qwen3.6-Plus comparison table](https://qwen.ai/blog?id=qwen3.6) |
| [FrontierMath v2 (Tiers 1-3)](/benchmarks/frontiermathv2tiers13) | 34.386% | [Epoch AI FrontierMath v2 leaderboard](https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2) |
| [FrontierMath v2 (Tier 4)](/benchmarks/frontiermathv2tier4) | 4.878% | [Epoch AI FrontierMath v2 leaderboard](https://epoch.ai/benchmarks/frontiermath-tier-4-v2?view=graph&tab=leaderboard) |

## Other Anthropic Models

- [Claude Opus 5.5](/models/claude-opus-5-5) - Score: 86.56
- [Claude Fable 5.1](/models/claude-fable-5-1) - Score: 83.18
- [Claude Sonnet 5.5](/models/claude-sonnet-5-5) - Score: 82.18
- [Claude Fable 5](/models/claude-fable) - Score: 81.27
- [Claude Opus 5](/models/claude-opus-5) - Score: 79.63
- [Claude Haiku 5.5](/models/claude-haiku-5-5) - Score: 70.04
- [Claude Opus 4.8](/models/claude-opus-4-8) - Score: 70.01
- [Claude Opus 4.7 (Adaptive)](/models/claude-opus-4-7-adaptive) - Score: 68.96
- [Claude Opus 4.7](/models/claude-opus-4-7) - Score: 66.74
- [Claude Sonnet 5](/models/claude-sonnet-5) - Score: 64.84
- [Claude Opus 4.6](/models/claude-opus-4-6) - Score: 62.39
- [Claude Sonnet 4.6](/models/claude-sonnet-4-6) - Score: 55.89
- [Claude Opus 4.5 Thinking](/models/claude-opus-4-5-thinking) - Score: 54.1
- [Claude Sonnet 4.5](/models/claude-sonnet-4-5) - Score: 47.96
- [Claude Haiku 4.5](/models/claude-haiku-4-5) - Score: 41.16
- [Claude 4.1 Opus](/models/claude-4-1-opus) - Score: 40.05
- [Claude 4.1 Opus Thinking](/models/claude-4-1-opus-thinking) - Score: 39.37
- [Claude 4 Sonnet](/models/claude-4-sonnet) - Score: 38.08
- [Claude 3 Opus](/models/claude-3-opus) - Score: 28.49
- [Claude 3.5 Sonnet](/models/claude-3-5-sonnet) - Score: 27.73
- [Claude 3 Haiku](/models/claude-3-haiku) - Score: 14.19
- [Claude Mythos 5](/models/claude-mythos-5) - Score: not computed
- [Claude 4 Opus Thinking](/models/claude-4-opus-thinking) - Score: not computed
- [Claude Opus 4.6 (Adaptive)](/models/claude-opus-4-6-thinking) - Score: not computed
- [Claude 4 Opus](/models/claude-4-opus) - Score: not computed
- [Claude 3.7 Sonnet Thinking](/models/claude-3-7-sonnet-thinking) - Score: not computed
- [Claude 3.7 Sonnet](/models/claude-3-7-sonnet) - Score: not computed
- [Claude 3.5 Haiku](/models/claude-3-5-haiku) - Score: not computed
- [Claude Sonnet 4.5 Thinking](/models/claude-sonnet-4-5-thinking) - Score: not computed
- [Claude Mythos 5.1](/models/claude-mythos-5-1) - Score: not computed
- [Claude Mythos Preview](/models/claude-mythos-preview) - Score: not computed
- [Claude Haiku 4.5 Thinking](/models/claude-haiku-4-5-thinking) - Score: not computed