<!-- LLM_VERSION_INFO
FORMAT: text/markdown
CONTENT_TYPE: article
ORIGINAL_URL: https://www.vals.ai/models/anthropic_claude-sonnet-4-5-20250929-thinking
ALTERNATE_VERSION: models/anthropic_claude-sonnet-4-5-20250929-thinking/index.html (text/html)
EXTRACTION_DATE: 2026-04-17T00:43:51.698Z

This is the markdown version with text-only content (images converted to alt-text).
For rich formatting with images, request the HTML version at: models/anthropic_claude-sonnet-4-5-20250929-thinking/index.html
-->

### Open Weights & Proprietary

#### All Companies

### Release date

| Model                      | Release Date | 
|---------------------------|--------------|
| Claude Opus 4.7          | 4/16/2026    |
| Muse Spark                | 4/8/2026     |
| Gemma 4 31B IT           | 4/2/2026     |
| Qwen 3.6 Plus            | 4/2/2026     |
| GLM 5.1                  | 4/1/2026     |
| Trinity Large Thinking    | 4/1/2026     |
| GPT 5.4 Mini             | 3/17/2026    |
| GPT 5.4 Nano             | 3/17/2026    |
| MiniMax-M2.7             | 3/17/2026    |
| Grok 4.20 (Reasoning)    | 3/9/2026     |
| GPT 5.4                  | 3/5/2026     |
| Gemini 3.1 Flash Lite Preview | 2/24/2026 |
| GPT 5.3 Codex            | 2/23/2026    |
| Qwen 3.5 Flash           | 2/19/2026    |
| Gemini 3.1 Pro Preview (02/26) | 2/17/2026 |
| Claude Sonnet 4.6        | 2/16/2026    |
| Qwen 3.5 Plus            | 2/12/2026    |
| MiniMax-M2.5             | 2/12/2026    |
| MiniMax-M2.5             | 2/11/2026    |
| GLM 5                     | 2/5/2026     |
| Claude Opus 4.6 (Nonthinking) | 2/5/2026 |
| Claude Opus 4.6 (Thinking) | 1/26/2026   |
| Kimi K2.5                | 1/23/2026    |
| Qwen 3 Max Thinking      | 12/23/2025   |
| MiniMax-M2.1             | 12/22/2025   |
| GLM 4.7                  | 12/17/2025   |
| Gemini 3 Flash (12/25)   | 12/17/2025   |
| MiMo V2 Flash            | 12/11/2025   |
| GPT 5.2                  | 12/11/2025   |
| GPT 5.2 Codex            | 12/11/2025   |

### Claude Sonnet 4.5 (Thinking)

**Release Date:** 9/29/2025  
**Accuracy (Vals Index):** 59.88% ± 1.97  
**Latency (Vals Index):** 276.83s  
**Cost/Test (Vals Index):** $0.66  
**Context Window:** 1M  
**Max Output Tokens:** 64k  
**Input Modality:** Hyperparameter settings

**Default Provider:** Anthropic

**Temperature:** 1  
**Top P:** Default  
**Top K:** Default  
**Max Output Tokens:** 64,000

### Benchmarks

#### Accuracy Rankings

- [Vals Index](/content/benchmarks/vals_index/index.html) 
   -171.02% ± 1.97 ; 114/40

- [Vals Multimodal Index](/content/benchmarks/vals_multimodal_index/index.html) 
   -196.54% ± 1.55 ; 79/28

- [CaseLaw (v2)](/content/benchmarks/case_law_v2/index.html) 
   -237.11% ± 1.55 ; 161/47

- [CorpFin](/content/benchmarks/corp_fin_v2/index.html) 
   -270.72% ± 0.96 ; 420/97

- [Finance Agent (v1.1)](/content/benchmarks/finance_agent/index.html) 
   -270.55% ± 2.86 ; 204/45

- [MedCode](/content/benchmarks/medcode/index.html) 
   -247.23% ± 2.00 ; 242/51

- [MedScribe](/content/benchmarks/medscribe/index.html) 
   -528.52% ± 1.87 ; 315/51

- [MortgageTax](/content/benchmarks/mortgage_tax/index.html) 
   -448.60% ± 0.96 ; 378/69

- [ProofBench](/content/benchmarks/proof_bench/index.html) 
   -147.94% ± 3.94 ; 133/24

- [SAGE](/content/benchmarks/sage/index.html) 
   -310.45% ± 3.21 ; 213/49

- [TaxEval (v2)](/content/benchmarks/tax_eval_v2/index.html) 
   -695.02% ± 0.86 ; 835/104

- [AIME](/content/benchmarks/aime/index.html) 
   -917.69% ± 0.69 ; 783/96

- [GPQA](/content/benchmarks/gpqa/index.html) 
   -929.15% ± 2.25 ; 907/99

- [IOI](/content/benchmarks/ioi/index.html) 
   -227.54% ± 5.92 ; 497/50

- [LiveCodeBench](/content/benchmarks/lcb/index.html) 
   -1005.98% ± 1.13 ; 888/103

- [LegalBench](/content/benchmarks/legal_bench/index.html) 
   -1231.25% ± 0.45 ; 1595/116

- [MedQA](/content/benchmarks/medqa/index.html) 
   -1500.79% ± 0.20 ; 1363/95

- [MMLU Pro](/content/benchmarks/mmlu_pro/index.html) 
   -1496.41% ± 0.39 ; 1604/97

- [MMMU Pro](/content/benchmarks/mmmu/index.html) 
   -1461.89% ± 0.97 ; 859/66

- [SWE-bench](/content/benchmarks/swebench/index.html) 
   -1387.37% ± 2.05 ; 398/41

- [Terminal-Bench 2.0](/content/benchmarks/terminal-bench-2/index.html) 
   -884.24% ± 5.25 ; 775/52

### Contact us

Or send us an email at [contact@vals.ai](mailto:contact@vals.ai)

**Proprietary Benchmarks:** [contact us](/content/models/anthropic_claude-sonnet-4-5-20250929-thinking#contact-form/index.html) to get access.