# GDPval-AA → OSWorld-Verified

Calibration · https://benchgap.net/calibration/gdpvalaanormalized/current/to/osworld-verified/current · data retrieved 2026-11-18

OSWorld-Verified is estimated from GDPval-AA with a linear curve fitted on 21 models measured on both: y = 0.5293·x + 0.5541, R² = 0.49, cross-validated error 8.4 pp. It is used for 58 estimates.

| Estimated model | GDPval-AA | OSWorld-Verified | Source |
|---|---|---|---|
| [Claude Opus 5.5](https://benchgap.net/model/claude-opus-5-5.md) | 68.3% | 91.6% | estimated ± 8.4 pp, low confidence |
| [Muse Wonder Full](https://benchgap.net/model/muse-wonder-full.md) | 67.9% | 91.3% | estimated ± 8.4 pp, low confidence |
| [Claude Sonnet 5.5](https://benchgap.net/model/claude-sonnet-5-5.md) | 66.9% | 90.8% | estimated ± 8.4 pp, low confidence |
| [Muse Wonder](https://benchgap.net/model/muse-wonder.md) | 63.5% | 89.0% | estimated ± 8.4 pp, low confidence |
| [Claude Fable 5.1](https://benchgap.net/model/claude-fable-5-1.md) | 62.7% | 88.6% | estimated ± 8.4 pp, low confidence |
| [Grok 4.7](https://benchgap.net/model/grok-4-7.md) | 60.7% | 87.5% | estimated ± 8.4 pp, low confidence |
| [Qwen3.8 Max Preview](https://benchgap.net/model/qwen3-8-max-preview.md) | 58.3% | 86.3% | estimated ± 8.4 pp, low confidence |
| [Gemini 4 Argon](https://benchgap.net/model/gemini-4-argon.md) | 56.2% | 85.2% | estimated ± 8.4 pp, low confidence |
| [Claude Haiku 5.5](https://benchgap.net/model/claude-haiku-5-5.md) | 56.0% | 85.1% | estimated ± 8.4 pp, low confidence |
| [GPT-6.1 Sol](https://benchgap.net/model/gpt-6-1-sol.md) | 54.8% | 84.4% | estimated ± 8.4 pp, low confidence |
| [GPT-6 Sol](https://benchgap.net/model/gpt-6-sol.md) | 50.4% | 82.1% | estimated ± 8.4 pp, low confidence |
| [Muse Spark 1.2](https://benchgap.net/model/muse-spark-1-2.md) | 48.6% | 81.1% | estimated ± 8.4 pp, low confidence |
| [GPT-6 Luna](https://benchgap.net/model/gpt-6-luna.md) | 46.6% | 80.1% | estimated ± 8.4 pp, low confidence |
| [Muse Spark Open](https://benchgap.net/model/muse-spark-open.md) | 45.1% | 79.3% | estimated ± 8.4 pp, low confidence |
| [Grok 4.5](https://benchgap.net/model/grok-4-5.md) | 44.2% | 78.8% | estimated ± 8.4 pp, low confidence |
| [Apodex 1.1 Mini](https://benchgap.net/model/apodex-1-1-mini.md) | 34.4% | 73.6% | estimated ± 8.4 pp, low confidence |
| [Quasar 438B](https://benchgap.net/model/quasar-438b.md) | 34.1% | 73.5% | estimated ± 8.4 pp, low confidence |
| [Ling 3.0 Flash VL](https://benchgap.net/model/ling-3-0-flash-vl.md) | 33.0% | 72.9% | estimated ± 8.4 pp, low confidence |
| [Hy3](https://benchgap.net/model/hy3.md) | 28.2% | 70.3% | estimated ± 8.4 pp, low confidence |
| [Kimi K2.7 Code](https://benchgap.net/model/kimi-k2-7-code.md) | 26.9% | 69.6% | estimated ± 8.4 pp, low confidence |
| [A.X K2](https://benchgap.net/model/a-x-k2.md) | 23.0% | 67.6% | estimated ± 8.4 pp, low confidence |
| [GPT-5](https://benchgap.net/model/gpt-5.md) | 20.9% | 66.5% | estimated ± 8.4 pp, low confidence |
| [MiniCPM5-2B](https://benchgap.net/model/minicpm5-2b.md) | 10.4% | 60.9% | estimated ± 8.4 pp, low confidence |
| [MiMo-V2-Flash](https://benchgap.net/model/mimo-v2-flash.md) | 6.4% | 58.8% | estimated ± 8.4 pp, low confidence |
| [Granite 4.2 30B](https://benchgap.net/model/granite-4-2-30b.md) | 3.7% | 57.4% | estimated ± 8.4 pp, low confidence |
| [Gemma 4 26B A4B](https://benchgap.net/model/gemma-4-26b-a4b.md) | 3.2% | 57.1% | estimated ± 8.4 pp, low confidence |
| [Ling 3.0 Tiny](https://benchgap.net/model/ling-3-0-tiny.md) | 3.0% | 57.0% | estimated ± 8.4 pp, low confidence |
| [Command A+](https://benchgap.net/model/command-a-plus.md) | 0.7% | 55.8% | estimated ± 8.4 pp, low confidence |
| [Celeris-1](https://benchgap.net/model/celeris-1.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Claude 3.5 Haiku](https://benchgap.net/model/claude-3-5-haiku.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [DeepSeek V3](https://benchgap.net/model/deepseek-v3.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [DeepSeek V3 0324](https://benchgap.net/model/deepseek-v3-0324.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Gemma 3 27B](https://benchgap.net/model/gemma-3-27b.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Gemma 4 12B](https://benchgap.net/model/gemma-4-12b.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Gemma 4 E2B](https://benchgap.net/model/gemma-4-e2b.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Gemma 4 E4B](https://benchgap.net/model/gemma-4-e4b.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [GPT-4.1 mini](https://benchgap.net/model/gpt-4-1-mini.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [GPT-4.1 nano](https://benchgap.net/model/gpt-4-1-nano.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [GPT-4o](https://benchgap.net/model/gpt-4o.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [GPT-4o mini](https://benchgap.net/model/gpt-4o-mini.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [GPT-OSS 20B](https://benchgap.net/model/gpt-oss-20b.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Granite 4.2 3B](https://benchgap.net/model/granite-4-2-3b.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Granite 4.2 8B](https://benchgap.net/model/granite-4-2-8b.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [K-Exaone](https://benchgap.net/model/k-exaone.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Ling 2.6 Flash](https://benchgap.net/model/ling-2-6-flash.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Llama 3.3 70B](https://benchgap.net/model/llama-3-3-70b.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Llama 4 Maverick](https://benchgap.net/model/llama-4-maverick.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Llama 4 Scout](https://benchgap.net/model/llama-4-scout.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Mercury 2.5](https://benchgap.net/model/mercury-2-5.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Mistral Large 3](https://benchgap.net/model/mistral-large-3.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Mistral Small 3.1](https://benchgap.net/model/mistral-small-3-1.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Mistral Small 4](https://benchgap.net/model/mistral-small-4.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Nemotron 3 Nano 30B](https://benchgap.net/model/nemotron-3-nano-30b.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Nemotron 3 Nano Omni 30B A3B](https://benchgap.net/model/nemotron-3-nano-omni-30b-a3b.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [North Mini Code](https://benchgap.net/model/north-mini-code-1-0.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Solar Pro 3](https://benchgap.net/model/solar-pro-3.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Trinity-Large-Preview](https://benchgap.net/model/trinity-large-preview.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |
| [Ultravox v0.6 Llama 3.3 70B](https://benchgap.net/model/ultravox-v0-6-llama-3-3-70b.md) | 0.0% | 55.4% | estimated ± 8.4 pp, low confidence |

## Fitted on

| Model | GDPval-AA | OSWorld-Verified |
|---|---|---|
| [Claude Fable 5](https://benchgap.net/model/claude-fable.md) | 55.5% | 85.0% |
| [Claude Opus 4.7](https://benchgap.net/model/claude-opus-4-7.md) | 42.6% | 78.0% |
| [Claude Opus 4.8](https://benchgap.net/model/claude-opus-4-8.md) | 47.7% | 83.4% |
| [Claude Sonnet 5](https://benchgap.net/model/claude-sonnet-5.md) | 48.2% | 81.2% |
| [Gemini 3.5 Flash](https://benchgap.net/model/gemini-3-5-flash.md) | 42.2% | 78.4% |
| [Gemini 3.5 Flash-Lite](https://benchgap.net/model/gemini-3-5-flash-lite.md) | 24.2% | 74.0% |
| [Gemini 3.6 Flash](https://benchgap.net/model/gemini-3-6-flash.md) | 39.2% | 83.0% |
| [GPT-5.4](https://benchgap.net/model/gpt-5-4.md) | 37.3% | 75.0% |
| [GPT-5.4 mini](https://benchgap.net/model/gpt-5-4-mini.md) | 25.6% | 72.1% |
| [GPT-5.4 nano](https://benchgap.net/model/gpt-5-4-nano.md) | 22.4% | 39.0% |
| [GPT-5.5](https://benchgap.net/model/gpt-5-5.md) | 42.5% | 78.7% |
| [Kimi K2.6](https://benchgap.net/model/kimi-2-6.md) | 26.9% | 73.1% |
| [Kimi K2.5](https://benchgap.net/model/kimi-k2-5.md) | 17.0% | 63.3% |
| [MiMo-V2.6-Flash](https://benchgap.net/model/mimo-v2-6-flash.md) | 55.4% | 80.8% |
| [MiMo-V2.6-Pro](https://benchgap.net/model/mimo-v2-6-pro.md) | 59.2% | 82.0% |
| [MiniMax M3](https://benchgap.net/model/minimax-m3.md) | 37.1% | 70.1% |
| [Muse Glimmer 30B](https://benchgap.net/model/muse-glimmer-30b.md) | 14.2% | 65.9% |
| [Muse Spark 1.1](https://benchgap.net/model/muse-spark-1-1.md) | 35.6% | 80.8% |
| [Qwen3.5-122B-A10B](https://benchgap.net/model/qwen3-5-122b-a10b.md) | 15.7% | 58.0% |
| [Qwen3.7 Plus](https://benchgap.net/model/qwen3-7-plus.md) | 13.3% | 73.3% |
| [Qwen3.8-27B](https://benchgap.net/model/qwen3-8-27b.md) | 45.9% | 84.3% |
