Open Weights & Proprietary
All Companies
| Release Date | Model Name | Provider |
|---|---|---|
| 4/16/2026 | Claude Opus 4.7 | |
| 4/8/2026 | Muse Spark | |
| 4/2/2026 | Gemma 4 31B IT | |
| 4/2/2026 | Qwen 3.6 Plus | |
| 4/1/2026 | GLM 5.1 | |
| 4/1/2026 | Trinity Large Thinking | |
| 3/17/2026 | GPT 5.4 Mini | |
| 3/17/2026 | GPT 5.4 Nano | |
| 3/17/2026 | MiniMax-M2.7 | |
| 3/9/2026 | Grok 4.20 (Reasoning) | |
| 3/5/2026 | GPT 5.4 | |
| 3/3/2026 | 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 |
GPT 5.1 Details
Release Date: 11/13/2025
Provider:
- Accuracy (Vals Index): 60.38% ± 2.00
- Latency (Vals Index): 411.84s
- Cost/Test (Vals Index): $0.36
- Context Window: 400k
- Max Output Tokens: 128k
Hyperparameter Settings
- Temperature: Default
- Top P: Default
- Top K: Default
- Max Output Tokens: 128,000
- Reasoning Effort: High
Benchmarks
- Accuracy Rankings: -73.04% ± 2.00
- Vals Multimodal Index: -89.68% ± 1.57
- CaseLaw (v2): -138.36% ± 0.75
- CorpFin: -145.62% ± 0.95
- Finance Agent (v1.1): -150.06% ± 2.80
- MedCode: -167.74% ± 2.15
- MedScribe: -324.77% ± 1.94
- MortgageTax: -259.77% ± 0.93
- SAGE: -208.31% ± 3.16
- TaxEval (v2): -407.63% ± 0.85
- AIME: -570.87% ± 0.62
- GPQA: -591.89% ± 1.71
- IOI: -163.35% ± 7.34
- LiveCodeBench: -727.29% ± 0.98
- LegalBench: -801.22% ± 0.40
- MedQA: -981.26% ± 0.17
- MMLU Pro: -962.55% ± 0.34
- MMMU Pro: -1011.55% ± 0.90
- SWE-bench: -923.74% ± 2.06
- Terminal-Bench 2.0: -645.52% ± 5.30
Contact Information
For proprietary benchmarks or general inquiries, please email contact@vals.ai.
Read about our methodology.