Calibration
AA Coding Index → FrontierCode 1.1 Main
FrontierCode 1.1 Main is estimated from AA Coding Index with a inverse Michaelis–Menten curve fitted on 8 models measured on both: y = 0.32262·(x − 0.0000) / (0.0000 + 1.2617 − x), R² = 0.87, cross-validated error 3.8 pp. It is used for 46 estimates.
| Estimated model | AA Coding Index | FrontierCode 1.1 Main | Source |
|---|---|---|---|
| Apodex 1.1 Mini | 60.8% | 30.0% | estimated ± 3.8 pp, high confidence |
| Celeris-1 | 14.4% | 4.2% | estimated ± 3.8 pp, medium confidence |
| Claude 3 Opus | 19.5% | 5.9% | estimated ± 3.8 pp, medium confidence |
| Command A+ | 27.9% | 9.1% | estimated ± 3.8 pp, medium confidence |
| Gemini 1.5 Pro | 23.6% | 7.4% | estimated ± 3.8 pp, medium confidence |
| Gemini 3.5 Flash-Lite | 49.3% | 20.7% | estimated ± 3.8 pp, medium confidence |
| Gemma 3 27B | 10.1% | 2.8% | estimated ± 3.8 pp, medium confidence |
| Gemma 4 12B | 31.0% | 10.5% | estimated ± 3.8 pp, medium confidence |
| Gemma 4 26B A4B | 39.3% | 14.6% | estimated ± 3.8 pp, medium confidence |
| Gemma 4 31B | 43.4% | 16.9% | estimated ± 3.8 pp, medium confidence |
| Gemma 4 E2B | 7.2% | 2.0% | estimated ± 3.8 pp, medium confidence |
| Gemma 4 E4B | 9.4% | 2.6% | estimated ± 3.8 pp, medium confidence |
| GLM-5.1 | 55.8% | 25.6% | estimated ± 3.8 pp, medium confidence |
| GPT-4.1 nano | 11.1% | 3.1% | estimated ± 3.8 pp, medium confidence |
| GPT-4 Turbo | 21.5% | 6.6% | estimated ± 3.8 pp, medium confidence |
| GPT-4o mini | 11.4% | 3.2% | estimated ± 3.8 pp, medium confidence |
| GPT-5.1 | 49.4% | 20.8% | estimated ± 3.8 pp, medium confidence |
| GPT-5.4 nano | 56.1% | 25.8% | estimated ± 3.8 pp, medium confidence |
| GPT-5 (high) | 37.8% | 13.8% | estimated ± 3.8 pp, medium confidence |
| GPT-OSS 120B | 30.4% | 10.3% | estimated ± 3.8 pp, medium confidence |
| GPT-OSS 20B | 20.7% | 6.3% | estimated ± 3.8 pp, medium confidence |
| Grok 4.3 | 42.3% | 16.2% | estimated ± 3.8 pp, medium confidence |
| Hy3 | 58.8% | 28.2% | estimated ± 3.8 pp, high confidence |
| K-Exaone | 32.1% | 11.0% | estimated ± 3.8 pp, medium confidence |
| LFM2.5-2.6B | 7.7% | 2.1% | estimated ± 3.8 pp, medium confidence |
| Ling 2.6 Flash | 25.3% | 8.1% | estimated ± 3.8 pp, medium confidence |
| Ling 3.0 Flash | 50.6% | 21.6% | estimated ± 3.8 pp, medium confidence |
| Ling 3.0 Flash FP8 | 50.6% | 21.6% | estimated ± 3.8 pp, medium confidence |
| Llama 4 Maverick | 16.3% | 4.8% | estimated ± 3.8 pp, medium confidence |
| Llama 4 Scout | 8.2% | 2.2% | estimated ± 3.8 pp, medium confidence |
| MiMo-V2.5-Pro | 60.2% | 29.4% | estimated ± 3.8 pp, high confidence |
| MiniMax M2.7 | 52.6% | 23.1% | estimated ± 3.8 pp, medium confidence |
| Mistral Large 3 | 20.1% | 6.1% | estimated ± 3.8 pp, medium confidence |
| Mistral Small 4 | 26.6% | 8.6% | estimated ± 3.8 pp, medium confidence |
| Mistral Small 4 (Reasoning) | 26.6% | 8.6% | estimated ± 3.8 pp, medium confidence |
| Nemotron 3 Nano 30B | 14.4% | 4.1% | estimated ± 3.8 pp, medium confidence |
| Nemotron 3 Nano Omni 30B A3B | 13.8% | 3.9% | estimated ± 3.8 pp, medium confidence |
| Nemotron 3 Super 100B | 37.7% | 13.8% | estimated ± 3.8 pp, medium confidence |
| o1 | 39.7% | 14.8% | estimated ± 3.8 pp, medium confidence |
| o1-preview | 34.1% | 11.9% | estimated ± 3.8 pp, medium confidence |
| Quasar 438B | 61.2% | 30.4% | estimated ± 3.8 pp, high confidence |
| Qwen3.8 Max Preview | 71.8% | 42.6% | estimated ± 3.8 pp, high confidence |
| Step 3.7 Flash | 39.6% | 14.7% | estimated ± 3.8 pp, medium confidence |
| Trinity-Large-Preview | 25.8% | 8.3% | estimated ± 3.8 pp, medium confidence |
| Trinity-Large-Thinking | 25.8% | 8.3% | estimated ± 3.8 pp, medium confidence |
| Ultravox v0.6 Llama 3.3 70B | 11.9% | 3.4% | estimated ± 3.8 pp, medium confidence |