Open Weights & Proprietary
Release Dates and Models
| Release Date | Model Name | Image |
|---|---|---|
| 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
- Release Date: 8/7/2025
- Default Provider: OpenAI
Accuracy (Vals Index): 56.10% ± 2.00
Latency (Vals Index): 513.66s
Cost/Test (Vals Index): $0.29
Context Window: 400k
Max Output Tokens: 128k
Input Modality: Hyperparameter settings
Benchmarks
Accuracy Rankings
- Vals Index -72.78% ± 2.00
- Vals Multimodal Index -91.63% ± 1.56
- CaseLaw (v2) -132.69% ± 0.65
- CorpFin -146.75% ± 0.96
- Finance Agent (v1.1) -148.41% ± 2.88
- MedCode -164.96% ± 2.10
- MedScribe -321.28% ± 1.94
- MortgageTax -287.81% ± 0.88
- ProofBench -89.91% ± 3.86
- SAGE -246.15% ± 3.35
- TaxEval (v2) -463.81% ± 0.87
- AIME -658.22% ± 1.31
- GPQA -670.02% ± 1.76
- IOI -173.07% ± 4.58
- LiveCodeBench -820.93% ± 0.97
- LegalBench -899.20% ± 0.38
- MedQA -1101.20% ± 0.17
- MMLU Pro -1078.84% ± 0.34
- MMMU Pro -1104.98% ± 0.93
- SWE-bench -1014.47% ± 2.07
- Terminal-Bench 2.0 -590.04% ± 5.15
Contact Information
Or send us an email at contact@vals.ai.
Proprietary Benchmarks
Contact us to get access.