# Vals GPQA Diamond → AA-GPQA Diamond

Calibration · https://benchgap.net/calibration/1540 · data retrieved 2026-10-29

AA-GPQA Diamond is estimated from Vals GPQA Diamond with a offset logistic curve fitted on 46 models measured on both: y = 0.6876 + (0.9519 − 0.6876) / (1 + exp(−19.21·(x − 0.8131))), R² = 0.79, cross-validated error 3.9 pp. It is used for 8 estimates.

| Estimated model | Vals GPQA Diamond | AA-GPQA Diamond | Source |
|---|---|---|---|
| [GLM-5.3-Flash](https://benchgap.net/model/glm-5-3-flash.md) | 86.4% | 88.0% | estimated ± 3.9 pp, high confidence |
| [Qwen3.5 Flash](https://benchgap.net/model/qwen3-5-flash.md) | 82.8% | 83.9% | estimated ± 3.9 pp, high confidence |
| [MiMo-V2.5](https://benchgap.net/model/mimo-v2-5.md) | 81.6% | 82.3% | estimated ± 3.9 pp, high confidence |
| [Gemini 3.1 Flash-Lite](https://benchgap.net/model/gemini-3-1-flash-lite.md) | 81.1% | 81.7% | estimated ± 3.9 pp, high confidence |
| [Claude Haiku 4.5](https://benchgap.net/model/claude-haiku-4-5.md) | 72.2% | 72.7% | estimated ± 3.9 pp, high confidence |
| [GLM-4.5](https://benchgap.net/model/glm-4-5.md) | 72.2% | 72.7% | estimated ± 3.9 pp, high confidence |
| [Laguna XS.2](https://benchgap.net/model/laguna-xs-2.md) | 55.1% | 68.9% | estimated ± 3.9 pp, high confidence |
| [Laguna M.1](https://benchgap.net/model/laguna-m-1.md) | 27.0% | 68.8% | estimated ± 3.9 pp, medium confidence |

## Fitted on

| Model | Vals GPQA Diamond | AA-GPQA Diamond |
|---|---|---|
| [Claude Fable 5](https://benchgap.net/model/claude-fable.md) | 93.2% | 92.6% |
| [Claude Fable 5.1](https://benchgap.net/model/claude-fable-5-1.md) | 93.4% | 93.7% |
| [Claude Opus 4.7](https://benchgap.net/model/claude-opus-4-7.md) | 90.2% | 88.5% |
| [Claude Opus 4.8](https://benchgap.net/model/claude-opus-4-8.md) | 92.4% | 92.0% |
| [Claude Opus 5](https://benchgap.net/model/claude-opus-5.md) | 93.4% | 93.2% |
| [Claude Sonnet 4.6](https://benchgap.net/model/claude-sonnet-4-6.md) | 85.6% | 79.9% |
| [Claude Sonnet 5](https://benchgap.net/model/claude-sonnet-5.md) | 88.9% | 91.1% |
| [DeepSeek V4 Flash 0731](https://benchgap.net/model/deepseek-v4-flash-0731.md) | 89.9% | 90.8% |
| [DeepSeek V4 Pro 0813](https://benchgap.net/model/deepseek-v4-pro-0813.md) | 92.4% | 92.8% |
| [Gemini 3.1 Pro](https://benchgap.net/model/gemini-3-1-pro.md) | 95.5% | 94.1% |
| [Gemini 3.5 Flash](https://benchgap.net/model/gemini-3-5-flash.md) | 92.7% | 92.2% |
| [Gemini 3.5 Flash-Lite](https://benchgap.net/model/gemini-3-5-flash-lite.md) | 83.8% | 83.8% |
| [Gemini 3.6 Flash](https://benchgap.net/model/gemini-3-6-flash.md) | 93.4% | 92.8% |
| [Gemini 3.7 Flash](https://benchgap.net/model/gemini-3-7-flash.md) | 93.9% | 94.5% |
| [Gemini 3.8 Flash](https://benchgap.net/model/gemini-3-8-flash.md) | 94.4% | 95.3% |
| [Gemini 3 Flash](https://benchgap.net/model/gemini-3-flash.md) | 87.9% | 81.2% |
| [GLM-4.6](https://benchgap.net/model/glm-4-6.md) | 74.5% | 63.2% |
| [GLM-4.7](https://benchgap.net/model/glm-4-7.md) | 80.1% | 85.9% |
| [GLM-5.1](https://benchgap.net/model/glm-5-1.md) | 84.5% | 86.8% |
| [GLM-5.2](https://benchgap.net/model/glm-5-2.md) | 85.6% | 89.5% |
| [GLM-5.3](https://benchgap.net/model/glm-5-3.md) | 88.1% | 91.7% |
| [GPT-5.4 mini](https://benchgap.net/model/gpt-5-4-mini.md) | 83.1% | 87.5% |
| [GPT-5.4 nano](https://benchgap.net/model/gpt-5-4-nano.md) | 77.5% | 81.7% |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 93.2% | 93.5% |
| [GPT-5.6 Luna](https://benchgap.net/model/gpt-5-6-luna.md) | 91.7% | 91.1% |
| [GPT-5.6 Sol](https://benchgap.net/model/gpt-5-6-sol.md) | 95.2% | 94.1% |
| [GPT-5.6 Terra](https://benchgap.net/model/gpt-5-6-terra.md) | 90.9% | 92.5% |
| [Grok 4.3](https://benchgap.net/model/grok-4-3.md) | 91.4% | 90.1% |
| [Grok 4.5](https://benchgap.net/model/grok-4-5.md) | 92.9% | 93.1% |
| [Grok 4.6](https://benchgap.net/model/grok-4-6.md) | 94.7% | 94.9% |
| [Inkling](https://benchgap.net/model/inkling.md) | 87.1% | 87.2% |
| [Inkling-Small](https://benchgap.net/model/inkling-small.md) | 83.6% | 89.5% |
| [Kimi K2.6](https://benchgap.net/model/kimi-2-6.md) | 89.1% | 91.1% |
| [Kimi K3](https://benchgap.net/model/kimi-k3.md) | 92.9% | 93.5% |
| [Ling 3.0 Flash](https://benchgap.net/model/ling-3-0-flash.md) | 84.8% | 85.5% |
| [MiMo-V2.5-Pro](https://benchgap.net/model/mimo-v2-5-pro.md) | 82.6% | 86.6% |
| [MiMo-V2-Flash](https://benchgap.net/model/mimo-v2-flash.md) | 59.3% | 65.6% |
| [MiniMax M2.7](https://benchgap.net/model/minimax-m2-7.md) | 86.6% | 87.4% |
| [MiniMax M3](https://benchgap.net/model/minimax-m3.md) | 92.7% | 92.9% |
| [Mistral Medium 3.5 128B](https://benchgap.net/model/mistral-medium-3-5-128b.md) | 34.8% | 74.8% |
| [Muse Spark](https://benchgap.net/model/muse-spark.md) | 89.6% | 88.4% |
| [Muse Spark 1.1](https://benchgap.net/model/muse-spark-1-1.md) | 91.2% | 89.8% |
| [Nemotron 3 Ultra](https://benchgap.net/model/nemotron-3-ultra.md) | 86.1% | 86.7% |
| [Qwen3.6 Plus](https://benchgap.net/model/qwen3-6-plus.md) | 87.4% | 88.2% |
| [Qwen3.7 Max](https://benchgap.net/model/qwen3-7-max.md) | 90.2% | 92.3% |
| [Qwen3.8-27B](https://benchgap.net/model/qwen3-8-27b.md) | 88.9% | 90.5% |