<!-- LLM_VERSION_INFO
FORMAT: text/markdown
CONTENT_TYPE: article
ORIGINAL_URL: https://www.vals.ai/models/google_gemini-3-flash-preview
ALTERNATE_VERSION: models/google_gemini-3-flash-preview/index.html (text/html)
EXTRACTION_DATE: 2026-04-17T00:49:33.753Z

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/google_gemini-3-flash-preview/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   |

---

### Gemini 3 Flash (12/25)

[Compare Models](/content/comparison?modelA=google%2Fgemini-3-flash-preview/index.html)

[Gemini 3 Flash (12/25)](https://ai.google.dev/gemini-api/docs/models)

**Release Date:** 12/17/2025

#### Accuracy (Vals Index)

- Accuracy: 60.61% ± 2.00
  
  
#### Latency (Vals Index)

- Latency: 382.73s

#### Cost/Test (Vals Index)

- Cost: $0.18

#### Context Window

- 1M

#### Max Output Tokens

- 66k

#### Input Modality

**Hyperparameter settings**

- Default Provider : Google

Some benchmarks may use different provider and parameters. Please refer to the benchmark page for more information.

#### Temperature

- 1

#### Top P

- Default

#### Top K

- Default

#### Max Output Tokens

- 65,536

#### Reasoning Effort

- high

---

### Benchmarks

| Benchmark                           | Accuracy            |  
|-------------------------------------|---------------------|  
| Vals Index                          | -66.80% ± 2.00      |  
| Vals Multimodal Index              | -88.77% ± 1.57      |  
| CaseLaw (v2)                       | -97.71% ± 0.11      |  
| CorpFin                             | -141.80% ± 0.93     |  
| Finance Agent (v1.1)               | -121.55% ± 2.78     |  
| MedCode                            | -168.22% ± 2.11     |  
| MedScribe                          | -244.74% ± 1.90     |  
| ProofBench                         | -60.46% ± 3.59      |  
| SAGE                               | -238.60% ± 3.40     |  
| TaxEval (v2)                      | -385.23% ± 0.86     |  
| Vibe Code Bench                    | -118.57% ± 3.95     |  
| AIME                               | -628.42% ± 0.52     |  
| GPQA                               | -642.94% ± 1.64     |  
| IOI                                | -321.42% ± 10.54    |  
| LiveCodeBench                      | -766.22% ± 1.00     |  
| LegalBench                         | -855.16% ± 0.36     |  
| MedQA                               | -1033.80% ± 0.18    |  
| MMLU Pro                           | -1044.32% ± 0.32    |  
| MMMU Pro                           | -1125.66% ± 0.79    |  
| SWE-bench                          | -1046.29% ± 1.94    |  
| Terminal-Bench 2.0                 | -781.43% ± 5.33     |

---

### Proprietary Benchmarks

- Contact us for access

### Academic Benchmarks

- Read about our [methodology](/content/methodology/index.html).