# Claude Sonnet 4.5 Thinking benchmark scores

Anthropic · model · https://benchgap.net/model/claude-sonnet-4-5-thinking · data retrieved 2026-11-22

As of 2026-11-22, Claude Sonnet 4.5 Thinking (Anthropic) has measured scores on 9 benchmarks and estimated scores on 45 more.

| Benchmark | Score | Source |
|---|---|---|
| [AA-GPQA Diamond](https://benchgap.net/b/aa-gpqa-diamond/current.md) | 85.5% | estimated ± 2.7 pp, high confidence |
| [AA-HLE](https://benchgap.net/b/aa-hle/current.md) | 29.6% | estimated ± 6.0 pp, medium confidence |
| [AA-SciCode](https://benchgap.net/b/aa-sci-code/current.md) | 48.9% | estimated ± 3.8 pp, high confidence |
| [Artificial Analysis Intelligence Index](https://benchgap.net/b/artificialanalysis/current.md) | 19.6% | estimated ± 5.8 pp, medium confidence |
| [CritPt](https://benchgap.net/b/critpt/current.md) | 8.7% | estimated ± 5.1 pp, medium confidence |
| [GPQA Diamond](https://benchgap.net/b/gpqa-diamond/current.md) | 85.1% | estimated ± 1.5 pp, medium confidence |
| [HLE](https://benchgap.net/b/hle/current.md) | 43.8% | estimated ± 6.1 pp, medium confidence |
| [LiveCodeBench v6](https://benchgap.net/b/livecodebench-v6/current.md) | 83.2% | estimated ± 2.2 pp, low confidence |
| [AA-Omniscience Accuracy](https://benchgap.net/b/omniscienceaccuracy/current.md) | 40.9% | estimated ± 6.5 pp, medium confidence |
| [SciCode](https://benchgap.net/b/scicode/current.md) | 47.2% | estimated ± 4.5 pp, medium confidence |
| [AA Coding Index](https://benchgap.net/b/aa-coding-index/current.md) | 52.5% | estimated ± 5.6 pp, medium confidence |
| [SWE-bench Verified](https://benchgap.net/b/swe-bench-verified/current.md) | 76.7% | estimated ± 4.4 pp, high confidence |
| [SWE-bench Pro](https://benchgap.net/b/swe-bench-pro/current.md) | 54.8% | estimated ± 2.9 pp, medium confidence |
| [MMLU-Pro](https://benchgap.net/b/mmlu-pro/current.md) | 86.2% | estimated ± 4.8 pp, high confidence |
| [FailureSensorIQ](https://benchgap.net/b/failuresensoriq/current.md) | 64.2% | estimated ± 1.7 pp, high confidence |
| [GPQA](https://benchgap.net/b/gpqa/current.md) | 85.0% | estimated ± 1.6 pp, high confidence |
| [MMLU](https://benchgap.net/b/mmlu/current.md) | 94.3% | estimated ± 1.2 pp, medium confidence |
| [Vals GPQA Diamond](https://benchgap.net/b/vals-gpqa-diamond/current.md) | 81.6% | measured |
| [Vals LiveCodeBench](https://benchgap.net/b/valslivecodebench/current.md) | 73.0% | measured |
| [Vals MMLU-Pro](https://benchgap.net/b/vals-mmlu-pro/current.md) | 87.4% | measured |
| [Chess Puzzles](https://benchgap.net/b/chesspuzzles/current.md) | 19.5% | estimated ± 12.3 pp, low confidence |
| [AA MMLU-Pro](https://benchgap.net/b/aa-mmlu-pro/current.md) | 87.9% | estimated ± 1.1 pp, high confidence |
| [ARC-AGI-1](https://benchgap.net/b/arcagi1/current.md) | 63.7% | measured |
| [ARC-AGI-2](https://benchgap.net/b/arc-agi-2/current.md) | 13.6% | measured |
| [CursorBench 3.1](https://benchgap.net/b/cursor-bench31/current.md) | 43.9% | estimated ± 5.8 pp, low confidence |
| [CursorBench 3.2](https://benchgap.net/b/cursor-bench32/current.md) | 52.7% | estimated ± 5.4 pp, low confidence |
| [FrontierCode 1.1 Main](https://benchgap.net/b/frontiercode/current.md) | 23.8% | estimated ± 5.2 pp, low confidence |
| [FrontierSWE v2](https://benchgap.net/b/frontierswev2/current.md) | 6.4% | estimated ± 9.5 pp, low confidence |
| [Mystery Game Puzzles](https://benchgap.net/b/mysterygamepuzzles/current.md) | 19.1% | estimated ± 4.7 pp, medium confidence |
| [NYT Connections](https://benchgap.net/b/nyt-connections/current.md) | 37.3% | measured |
| [Vals SWE-bench](https://benchgap.net/b/valsswebench/current.md) | 70.0% | measured |
| [VulcanBench v3](https://benchgap.net/b/vulcanbench%23vulcanbench-v3/current.md) | 78.6% | estimated ± 5.6 pp, low confidence |
| [CursorBench 4.0](https://benchgap.net/b/cursor-bench40/current.md) | 30.8% | estimated ± 3.4 pp, medium confidence |
| [DeepSWE](https://benchgap.net/b/deepswe/current.md) | 56.3% | estimated ± 7.2 pp, low confidence |
| [HLE w/o tools](https://benchgap.net/b/hlenotools/current.md) | 39.7% | estimated ± 4.9 pp, high confidence |
| [PostTrainBench v1.1](https://benchgap.net/b/posttrainbench%23posttrainbench-v1-1/current.md) | 15.4% | estimated ± 3.7 pp, medium confidence |
| [StealthMark](https://benchgap.net/b/stealthmark/current.md) | 41.3% | estimated ± 10.7 pp, low confidence |
| [ARC-AGI-3](https://benchgap.net/b/arcagi3/current.md) | 0.4% | estimated ± 8.6 pp, low confidence |
| [SkillsBench official leaderboard (BenchFlow)](https://benchgap.net/b/skillsbench/current.md) | 43.8% | estimated ± 6.1 pp, medium confidence |
| [BinaryAudit](https://benchgap.net/b/binaryaudit/current.md) | 35.1% | estimated ± 12.1 pp, low confidence |
| [CompileBench](https://benchgap.net/b/compilebench/current.md) | 84.4% | measured |
| [OTelBench](https://benchgap.net/b/otelbench/current.md) | 22.3% | estimated ± 6.6 pp, medium confidence |
| [Vibe Code Bench](https://benchgap.net/b/vibecodebench/current.md) | 22.6% | measured |
| [FACTS Multimodal](https://benchgap.net/b/facts-multimodal/current.md) | 22.7% | estimated ± 4.0 pp, medium confidence |
| [NL2Repo](https://benchgap.net/b/nl2repo/current.md) | 40.1% | estimated ± 4.7 pp, high confidence |
| [PostTrainBench v1](https://benchgap.net/b/posttrainbench%23posttrainbench-v1/current.md) | 19.0% | estimated ± 3.1 pp, medium confidence |
| [AA LiveCodeBench](https://benchgap.net/b/aa-live-code-bench/current.md) | 86.6% | estimated ± 2.6 pp, high confidence |
| [React Native Evals](https://benchgap.net/b/reactnativeevals/current.md) | 70.7% | estimated ± 3.0 pp, low confidence |
| [SWE-Rebench](https://benchgap.net/b/swe-rebench/current.md) | 42.8% | estimated ± 6.5 pp, low confidence |
| [PostTrainBench](https://benchgap.net/b/post-train-bench12/current.md) | 12.9% | estimated ± 3.7 pp, medium confidence |
| [LABBench2](https://benchgap.net/b/labbench2/current.md) | 81.7% | estimated ± 1.8 pp, low confidence |
| [ScarfBench](https://benchgap.net/b/scarfbench/current.md) | 41.2% | estimated ± 12.3 pp, low confidence |
| [OpenHarmony Bench v1.0](https://benchgap.net/b/openharmonybench%23openharmonybench-v1-0/current.md) | 51.1% | estimated ± 3.2 pp, high confidence |
| [BioBasicsBench](https://benchgap.net/b/biobasicsbench/current.md) | 34.3% | estimated ± 5.1 pp, low confidence |
